{ "schema_version": 1, "review_window": { "start": "2026-10-08", "end": "2026-10-12" }, "review_finalized_on": "2026-10-12", "policy": "observed-catalog-and-evidence-not-capability-v1", "counts": { "catalogued": 79, "not_catalogued": 1531 }, "accepted_counts": { "catalogued": 26, "not_catalogued": 494 }, "review_snapshot_modified": false, "implementation_complete": false, "papers": [ { "id": "2610.13935", "title": "Hide and Seek: HIDE Concepts to SEEK explanations for black box models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13925", "title": "Can machines reason non-verbally?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13917", "title": "Designing Protein Structures from Natural Language", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13912", "title": "RSI-Anything: Unlocking Recursive Self-Improvement with World Models", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "rsi-anything", "detail_path": "reproductions/2610.13912-rsi-anything/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-rsi-anything-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13910", "title": "When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13896", "title": "Structural Automata for Neural Semantic Parsing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13889", "title": "RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "rated", "detail_path": "reproductions/2610.13889-rated/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-rated-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13886", "title": "X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13858", "title": "LapMerge: Differentiable Exact-Budget Token Merging in Linear Time", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13841", "title": "Returning to Development States: When Full Sandbox Snapshots Help Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13840", "title": "Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13832", "title": "SpatialASM: Internalizing Active Mentalization for Spatial Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13821", "title": "Can Language Models Learn When to Abstain? Policy Learning and Calibrated Answer Selection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13806", "title": "FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "forte", "detail_path": "reproductions/2610.13806-forte/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.13797", "title": "REFLECT: Role-Aware Detection of Sentiment, Emotion, Politeness, and Formality", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13790", "title": "OccludeBench: Can VLMs Find What's Missing?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13783", "title": "UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13772", "title": "MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13767", "title": "DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "dualquant", "detail_path": "reproductions/2610.13767-dualquant/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-dualquant-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13763", "title": "Neurons++: A Unified Visual-Stream Framework for Image and Video Reconstruction from fMRI with Neural-to-Visual Interpretability", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13755", "title": "Matched-Context Group Policy Optimization for LLM Agent Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13744", "title": "A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13737", "title": "SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13735", "title": "Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "orthros", "detail_path": "reproductions/2610.13735-orthros/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-orthros-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13708", "title": "Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13703", "title": "A Baseline Assessment for the Agentic Web Technology Stack", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13697", "title": "Improving Semantic Coverage in AI Test & Evaluation through Generative Augmentation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13690", "title": "Transformer-based In-Context Score Operator Learning for Diffusion Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13668", "title": "(When) Should a Software Factory be Lights-off? Benchmarking Code Review Agents on Bug Detection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13663", "title": "A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13660", "title": "Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13653", "title": "A Critical Look at Power Sampling when Test Time Sharpening LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13647", "title": "A-SAW: The Agentic Software Architecture Workflow", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13636", "title": "Benchmarking Answer-Grounding Consistency in Remote Sensing Visual Question Answering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13635", "title": "PANDA: Prior-guided Attentional Dual-path Architecture", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13632", "title": "Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13630", "title": "Multi-Stream Attention Residuals", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "msar", "detail_path": "reproductions/2610.13630-msar/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-msar-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13617", "title": "Training User Simulators with Latent Intrinsic Feedback", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13605", "title": "zip2zip++: Towards Inference-Time Token Compression with Minimal Quality Loss", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13594", "title": "MENTOR: Learning from Failure with On-Policy Pedagogical Intervention", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13578", "title": "RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13563", "title": "Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13557", "title": "Probabilistic Ship Trajectory Forecasting using Transformer Models on AIS Data", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13548", "title": "Auditing VLM Benchmarks from Existing Evaluation Runs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13527", "title": "S-Space: Exploring Spatial Workspace in Multimodal Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13521", "title": "Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "road-mopd", "detail_path": "reproductions/2610.13521-road-mopd/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/road-mopd-a100-20261012.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13510", "title": "Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13504", "title": "Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13494", "title": "Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13485", "title": "Proactive Agentic Orchestration", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13481", "title": "Branching On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "branch-opd", "detail_path": "reproductions/2610.13481-branch-opd/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/branch-opd-a100-20261012.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13455", "title": "Agentic Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13439", "title": "Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13438", "title": "Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13421", "title": "REINS: Agent-guided Thread Scheduling for Concurrency Bug Detection and Reproduction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13416", "title": "Web$hell: A Unified Interface for Agentic Web Access", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13411", "title": "In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13398", "title": "Towards the Roof of the World: NLP Progress in Tibetan Languages", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13395", "title": "ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13370", "title": "Overcoming Data Imbalances with Expert Selection Biases", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13361", "title": "AgentSWE: Can Coding Agents Build the Agent You Actually Want?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13356", "title": "SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13348", "title": "Test-Time Memory Construction", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "t2mem", "detail_path": "reproductions/2610.13348-t2mem/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-t2mem-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13341", "title": "Understanding Mamba-3 Through Oscillatory Dynamics", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13337", "title": "Exploring Attention Sinks in Text-to-Image Transformers from Diffusion and Autoregressive Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13335", "title": "AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13334", "title": "PDE-PFN: Prior-Data Fitted Neural PDE Solver", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13330", "title": "Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13325", "title": "Taking Tokenization off the Host for Agentic LLM Serving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13321", "title": "Host-Aware Web Crawling for LLM Pretraining Data", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13296", "title": "PRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-Real", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13285", "title": "BoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "boundary-evo", "detail_path": "reproductions/2610.13285-boundary-evo/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/boundary-evo-a100-20261012.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13276", "title": "CopRoute: Dependence-Aware Conformal Routing for Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13273", "title": "Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13272", "title": "OWLET: On-Policy Weighted Learning via Evidence Transfer for Video Large Language Model Post-Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13267", "title": "Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13263", "title": "SheafPrune: Sheaf-Guided Graph Propagation for Visual Token Pruning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13262", "title": "Dual-Stream Memory for Vision-Language-Action Policies", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13261", "title": "Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13259", "title": "Beyond a Single Crop: Contextualized Embeddings for Player Re-Identification", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13257", "title": "CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "cast-opd", "detail_path": "reproductions/2610.13257-cast-opd/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/cast-opd-a100-20261012.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13253", "title": "Tabular Foundation Models Are Effectively Shallow", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13252", "title": "Vision Transformers Learn Word Meaning from Images Alone", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13239", "title": "Jag: Direct Box Prediction for Efficient Visual Grounding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13227", "title": "Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13208", "title": "How Much Computation Does Every Forecast Need? Structured Block Skipping in Two Time-Series Foundation Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13202", "title": "S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13194", "title": "Janus: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models", "review_decision": "accepted", "frozen_implementation_status": "registered_scoped_runtime; actual acceptance tracked separately", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "janus", "detail_path": "reproductions/2610.13194-janus/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-janus-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13172", "title": "RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13166", "title": "Scaling Agentic Data for Long-Horizon Terminal Intelligence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13154", "title": "From Glance to Focus: Mitigating Recognition Laziness in MLLMs for Fine-Grained Recognition", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13152", "title": "Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13144", "title": "Competence-Aware Orchestration for LLM-Based Multi-Agent Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13143", "title": "Measurable Semantic 3D Gaussian Splatting with Joint Region and Depth Supervision for Interactive Building Inspection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13128", "title": "Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13116", "title": "DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13111", "title": "What Do Visual-Head Discovery Scores Actually Find? Attention Source, Necessity, and Random-Control Pitfalls in Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13106", "title": "Scaling RNA Foundation Models through Iterative Refinement", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13102", "title": "From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13092", "title": "When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "jev-workflow", "detail_path": "reproductions/2610.13092-jev-workflow/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.13071", "title": "CAPE - Context-Aware Prioritization Engine for Vulnerability Scoring and Management", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13066", "title": "Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_frozen16", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13065", "title": "TestSuiteBench: Coding Agents Struggle to Generate Strong Test Suites from Specifications", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13064", "title": "CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13060", "title": "KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13058", "title": "Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13057", "title": "CoBe: A Benchmark For Conversational Counterfactual Text Editing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13056", "title": "A4-MR: Abnormality-aware Anatomical Alignment for MR", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13045", "title": "Redirecting Teacher Supervision: Temporal-Response-Guided Latent Distillation for Video-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13041", "title": "RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13040", "title": "Lightweight Time-Frequency Vibration Sensing for Consumer Device Condition Monitoring", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13035", "title": "GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13025", "title": "Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "evo2", "detail_path": "reproductions/2610.13025-evo2/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-evo2-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13022", "title": "Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13021", "title": "EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12998", "title": "Evaluating LLM Creativity through Long-Tail Performance", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12995", "title": "What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12981", "title": "The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12975", "title": "SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12961", "title": "MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12959", "title": "Video Codec-Guided Training-Free Token Compression for Video Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12957", "title": "JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12942", "title": "In-Context Learning Can Help Vision-Language Models Overcome Training Priors", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12932", "title": "SEEDS: Preview-Guided Evidence Admission for Search Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12927", "title": "Collaborative Learning and Reasoning over Model Slices", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12907", "title": "BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12885", "title": "Personalized Federated Direct Preference Optimization via LoRA Adapters", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12874", "title": "Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12866", "title": "CaptchaAgent: Verifiable Visual Reasoning for CAPTCHA Solving", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12864", "title": "Time Delay System for Sequence Modeling", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12849", "title": "Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12822", "title": "Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12813", "title": "VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12794", "title": "Meta-Reflective Evolution Effectively Improves Production AI Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12792", "title": "Large Language Models, Machine-Assisted Cultural Analytics, and the Agentic Turn", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12789", "title": "EvoBelief: Falsifiable World Models for Self-Improving LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12783", "title": "Shift-Aware Identity-Guided Latent Refinement for Referring Audio--Visual Segmentation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12757", "title": "MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12734", "title": "StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12711", "title": "Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12707", "title": "Unsupervised Multimodal Reward Modeling", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "umrm", "detail_path": "reproductions/2610.12707-umrm/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-umrm-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12703", "title": "Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12668", "title": "Recurrent Harness for Agentic Continual Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12655", "title": "CLEAT: Learning Value-Guided Clarification for Interactive Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12651", "title": "SynAct: Synergistic Active Feedback Learning for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12650", "title": "Feature Competition and Its Representational Origins in Vision Language Models: Evidence from the Stroop Paradigm", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12611", "title": "SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12602", "title": "Self-Preservation in Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12601", "title": "Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12598", "title": "Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12596", "title": "SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12593", "title": "Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12582", "title": "One Model to Loop Them All: Elastic Latent Recurrence for Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12575", "title": "Mind the Temporal Gap: Evaluating Video Models for Temporal Understanding in Driving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12569", "title": "SWE-Duel: Towards a Self-Scaling Arena for Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12566", "title": "Sample-Adaptive Zeroth-Order Post-Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12545", "title": "AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12461", "title": "OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12458", "title": "OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12451", "title": "VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12445", "title": "Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12427", "title": "FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12420", "title": "A Unified Bellman Operator for Safety-Critical Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12417", "title": "WOVEN: Weaving Visual World Modeling into Multimodal LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "woven", "detail_path": "reproductions/2610.12417-woven/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-woven-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12410", "title": "Predicting Alignment Generalization with Value Representations", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12402", "title": "SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12390", "title": "Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12382", "title": "WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12375", "title": "OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "ontrack", "detail_path": "agent-research/2610.12375-ontrack/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.12367", "title": "Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "sguid", "detail_path": "post-training/2610.12367-sguid/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/sguid-a100-20261012.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12360", "title": "Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12355", "title": "Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12341", "title": "Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12338", "title": "VFold: Symmetry-Aware Cross-Layer Value Cache Compression", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "vfold", "detail_path": "foundation-models/2610.12338-vfold/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/vfold-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12327", "title": "SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "sparse-decoding", "detail_path": "foundation-models/2610.12327-sparse-decoding/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/sparse-decoding-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12325", "title": "Prior or Feedback? What an LLM Uses When Adapting Neural Operators", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12310", "title": "Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12305", "title": "From What to Which: Decoding Modifier Grounding in Frozen MLLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12289", "title": "TestPrism: Rethinking Test Evaluation Beyond a Single Reference", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12281", "title": "Unlocking the Regulatory Genome by ARGUS: An Evidence-Constrained Agentic Framework for Interpreting Single Nucleotide Variants", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12274", "title": "HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12269", "title": "Cadence: Strategic Guidance for Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12266", "title": "DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12248", "title": "EgoVoice: Proactive Spoken Assistance from Egocentric Multimodal Streams", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12242", "title": "TokenRouter: Efficient Serving System for Token-Level LLM Routing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12235", "title": "Language Models as AI Research World Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12207", "title": "SciTBERT: A family of chronologically consistent language models for scientific and technological language processing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12201", "title": "SteerablePlex: Can We Steer Full-Duplex Models?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12183", "title": "A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12147", "title": "Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12144", "title": "Language-Specific Effects of Tokenizer Choice in Multilingual Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12135", "title": "Q-Shaped Options for Hierarchical Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12133", "title": "Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12126", "title": "SuperNav: An Agentic Navigation System for Any Task in Any Scene", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12124", "title": "Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "hippocam", "detail_path": "agent-research/2610.12124-hippocam/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/oct10-hippocam-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12086", "title": "EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "evoalloc", "detail_path": "agent-research/2610.12086-evoalloc/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/oct10-evoalloc-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12061", "title": "When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "race", "detail_path": "agent-research/2610.12061-race/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/oct10-race-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12060", "title": "Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "vimod", "detail_path": "multimodal-models/2610.12060-vimod/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/vimod-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12048", "title": "Do Not Train Away Uncertainty: Early Uncertainty Anchored Calibration", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12022", "title": "Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12002", "title": "Agentic-TTT: Training test-time policy for test-time training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11993", "title": "DataVista: Diagnosing Multimodal LLMs on Data Video Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11986", "title": "FearCaut-Qwen: Affective Steering in a Vision-Language Model Shifts the Decision Criterion for Hazard Assessment", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11966", "title": "MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11963", "title": "Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11959", "title": "MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11954", "title": "Look Where You Can: Active View Selection for CAD Reconstruction under Occlusion", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11948", "title": "When History Helps and Hurts: Selective History Use across Multimodal Turns", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11938", "title": "Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive Encoders", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11924", "title": "Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11920", "title": "Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11907", "title": "Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11899", "title": "Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11896", "title": "Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11862", "title": "LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11858", "title": "Trajectory-Guided Fault Localization for Agent Skill Evolution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11854", "title": "GRPODropout: Less is More for Online Reinforcement Learning Rollouts", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "grpo-dropout", "detail_path": "post-training/2610.11854-grpo-dropout/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/grpo-dropout-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11826", "title": "From Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11818", "title": "From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11810", "title": "Seek-and-View Reasoning for Multi-View Spatial Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11794", "title": "Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "memento3", "detail_path": "agent-research/2610.11794-memento3/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/memento3-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11776", "title": "DPPM: Dual-Path Parametric Memory for Personalized Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11773", "title": "Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11768", "title": "Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11766", "title": "Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11761", "title": "RAGenome: Scaling Retrieval-Based Genomic Language Models to Long Contexts", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11732", "title": "MemTrial: Learning When to Trust Memory in LLM Portfolio Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11725", "title": "Implementing the Spec Growth Engine: Preventing Spec-Code Divergence, and Growing the Spec with Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11716", "title": "4-Tensor Attention Model for Semantic Physical Reality", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11696", "title": "A 3D Characterization Framework for Intelligent Sequential Decision Making", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11678", "title": "TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11674", "title": "VESSI - VLM-Enhanced Support for Surveillance and Investigations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11663", "title": "Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11659", "title": "DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "dial-opd", "detail_path": "post-training/2610.11659-dial-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/dial-opd-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11655", "title": "Harness Evolution Hits a Ceiling: When Weight Training Should Begin", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11651", "title": "Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11647", "title": "One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11638", "title": "UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11618", "title": "PolyCodeEval: Benchmarking Multilingual Code Generation from Functions to Repositories", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11610", "title": "Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11605", "title": "NanoProof: Open and Efficient Automated Theorem Proving in Lean 4", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11602", "title": "Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11600", "title": "Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11593", "title": "Runnable Commit Untangling for Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11592", "title": "Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11585", "title": "Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11578", "title": "Chronos Enables Code Agents to Reason over Software Evolution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11573", "title": "Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11561", "title": "Workerville: Towards an Organizational Behavior Account of Agent Safety", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11559", "title": "SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11552", "title": "Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11548", "title": "Conditional Transfer from Controlled Pretraining Mixtures to Code", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11546", "title": "Learning to Orchestrate Evolutionary Search: Progression-Aware Deep Reinforcement Learning for Dynamic DE-CMA-ES Coordination in Optimization and Structural Model Updating", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11543", "title": "Learning the Loop, Not Just the Page: Execution-Grounded Loop Learning for Web Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11542", "title": "Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11523", "title": "When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11519", "title": "Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "residual-advantage", "detail_path": "post-training/2610.11519-residual-advantage/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/residual-advantage-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11514", "title": "SSCBench: Evaluating the Evidential Validity of Fault-Injection Tests for Tool-Using LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11510", "title": "Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11508", "title": "WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11501", "title": "Beyond Sequences: Distilling Structured Decision Memory for LLM Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11482", "title": "Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11469", "title": "SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11464", "title": "Who Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11461", "title": "Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11454", "title": "Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11451", "title": "SAIL: Scientific Agentic Intelligence via a Science-Aware Loop", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11447", "title": "Closed-loop evaluation of LLM agents for embedded software development", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11430", "title": "BioBigBird: A Sparse Attention Model for Long-Range Dependency Processing in Biomedical Text", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11422", "title": "Causal-fate dynamics of unrealized influence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11389", "title": "Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11384", "title": "Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11374", "title": "Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11373", "title": "From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11371", "title": "SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11370", "title": "RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11366", "title": "SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11363", "title": "UniData: Universal Multimodal Instruction Generation Pipeline", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11361", "title": "SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11358", "title": "RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11354", "title": "AdaptEvo: Adaptive Agent Learning with Evolving Supervision", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11352", "title": "RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11351", "title": "Deception by Omission: Language Models Knowingly Hide Their Mistakes", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11345", "title": "SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11334", "title": "ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11332", "title": "ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "recal", "detail_path": "post-training/2610.11332-recal/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/recal-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11329", "title": "PathLang: A Language-Centered Benchmark for Vision-Language Models in Computational Pathology", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11317", "title": "DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11316", "title": "MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11314", "title": "From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11312", "title": "MedBenchAgent: Towards Systematic Automation of Medical VLM Benchmark Construction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11310", "title": "FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11303", "title": "Efficient Multi-Granularity Knowledge Transfer for Radiology Report Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11299", "title": "DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11291", "title": "When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "semi-opd", "detail_path": "post-training/2610.11291-semi-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/semi-opd-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11287", "title": "REMORY: Learning Residual Memory for Context Compaction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11281", "title": "How to post-train on a surrogate: Envelope sampling mitigates reward hacking", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11253", "title": "LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11251", "title": "V-CoLA: Vision Token Compression with Linear Attention", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "vcola", "detail_path": "multimodal-models/2610.11251-vcola/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/vcola-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11247", "title": "Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "opd-learning-signals", "detail_path": "post-training/2610.11247-opd-learning-signals/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/opd-learning-signals-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11245", "title": "Read What Matters: Query-Adaptive Quantization for KV Caches", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11231", "title": "Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11226", "title": "When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11216", "title": "The Lattice of Transition Laws", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11214", "title": "Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11205", "title": "Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11196", "title": "Selective Listening: Mechanism-Guided Control of Audio Influence in Large Audio-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11188", "title": "What to Admit and How to Present: Governing Persistent Memory in LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11183", "title": "RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11179", "title": "Who Pays the Review Cost? Triage, Fairness, and Accountability in AI-authored Pull Requests", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11169", "title": "Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11167", "title": "PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "pivot", "detail_path": "post-training/2610.11167-pivot/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/pivot-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11161", "title": "VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11152", "title": "Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11148", "title": "SP-DocReader: Difference-Aware Self-Play for Precise Document OCR", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11144", "title": "Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11140", "title": "ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11136", "title": "The \"10th Juror\": Open-Set Standpoint Screening for Bureaucratic Bias Detection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11123", "title": "When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11113", "title": "DiscoVL: Unveiling Disentangled C ross-Modal Representation Learning via Orthogonal Adversarial Regularization for V ision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11111", "title": "Lapras: Latent Reasoning for Time Series Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11067", "title": "Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11064", "title": "Measuring and Mitigating Solution Mode Collapse in RLVR", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11039", "title": "Rendering-Free Lookahead for Question-Guided Active Vision", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11033", "title": "FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11030", "title": "NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11019", "title": "Mid-Training Language Models on Raw Video", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11015", "title": "Prompts versus Rules: Auditing and Controlling Speech Naturalness Behaviors in Voice User Simulators", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11008", "title": "Why LLM Agents Favor Their Group: Stakes, Observed Norms, and Reputation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11007", "title": "Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10990", "title": "Omni-Diffusion-Distill: Few-Step Distillation of Unified Multimodal Diffusion Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10988", "title": "Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10984", "title": "Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10974", "title": "Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10962", "title": "iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10961", "title": "Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10952", "title": "SPD-MetaFormer is what you need for small-data brain decoding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10947", "title": "RH-Detect: A Unified Benchmark for Reward Hacking Detection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10942", "title": "StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10932", "title": "World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10926", "title": "Adaptive Multi-Discriminator WGAN Framework for Resource-Constrained Internet of Vehicles Using Reinforcement Learning and Game Theory", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10920", "title": "Language Models for Page-Level Layout Decisions in E-commerce Search", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10918", "title": "Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10912", "title": "When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10906", "title": "Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10893", "title": "Less from More: Reinforcing Sparse Video Reasoning from Dense References", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10889", "title": "SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10878", "title": "Stochastic Teacher Intervention for Agentic On-Policy Distillation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10868", "title": "Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10858", "title": "RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10854", "title": "KDFP: A first-principles approach to knowledge distillation in large language models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10845", "title": "Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12517", "title": "TerraAgent: Demonstration-Grounded Multi-Agent Reasoning for Long-Context Remote Sensing Visual Question Answering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10833", "title": "On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12516", "title": "TraceICL: Thread-Resolved Demonstration Curation with Consistency Calibration for Robust Multimodal In-Context Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10787", "title": "NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10786", "title": "Plan-and-Patch: Diffusion Language Models for Agentic Planning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10782", "title": "VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10768", "title": "Strategic Investment Decision Making for Value Creation in Energy Transition: A Reinforcement Learning Approach", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10760", "title": "DOGS: Design-Space Sampling for Prompt-Driven Logo Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10740", "title": "Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10738", "title": "Lossy Compressive Text Autoencoders", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10697", "title": "On linearity or non-linearity in machine learning for quantum chaotic dynamics", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10536", "title": "Decoupling Exploration from Optimization in RLVR", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10533", "title": "EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10526", "title": "Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10520", "title": "Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10507", "title": "RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10491", "title": "Insights from Autoresearch for Solar Panel Segmentation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10478", "title": "Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10448", "title": "MemoCare: An Interactive Multimodal Mobile System for Automated Cognitive Screening", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10444", "title": "RunningTab: Direct Workspace Interaction with Environment-Side Tabs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10436", "title": "Detecting Adversarial Images through Response Profiles of Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10426", "title": "CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10659", "title": "Applying Security by Design at the Point of Execution: How Governed Security Requirements Affect the Security of AI-Generated Code", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10422", "title": "Which Rollout Taught It That? BehaviorTrace and the Limits of Training-Data Attribution in Online RL", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10411", "title": "Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10407", "title": "SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10400", "title": "Self-correction Optimization for Interleaved Multimodal Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10395", "title": "Executing Causal Structure Learning with Linear-Attention Transformers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10390", "title": "Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10385", "title": "OrBIT: Structure-Guided Embedding Compression", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10378", "title": "Document-Level Text Simplification in Estonian Using Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10655", "title": "Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10323", "title": "HAN-Mamba: Hierarchical Selective State Space Networks for Multi-Scale Financial Volatility Forecasting", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10320", "title": "LLM-Assisted Generation of Transparent, Open-Source Multiphysics Models of Electrochemical Devices", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10311", "title": "Fault-tolerant foundation models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10305", "title": "How Do Transformers Learn to Represent Symmetries?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10304", "title": "SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10302", "title": "Continual Graph Multi-Agent Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10286", "title": "$Δ$Representation: Geometry Supervised Representation Learning of Phenotypes via Counterfactual Reasoning for Medical VLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10265", "title": "Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10263", "title": "When Sub-Agents Work in Parallel: The Promises and Pitfalls of Dynamic Concurrency in Long-Horizon Coding Tasks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10258", "title": "QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10256", "title": "OOM-RL II: Reality Is an Oracle, Not a Debugger Provenance-Constrained Diagnosis in Continually Evolving Agent-Engineered Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10242", "title": "TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10238", "title": "Geometry-Supervised Visual Representation Learning for Multi-Phenotype Lesion Interpretation in Medical VLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10226", "title": "Why Software Engineering Is Indispensable in the Age of Coding Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10206", "title": "Computations of the slice genus and the unknotting number of links via machine learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10201", "title": "GAGR-Lab: Evaluating Joint Spatial-Geometric and Analytic Function Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10184", "title": "Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10183", "title": "VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10179", "title": "Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10163", "title": "Beyond Anonymous Captions: Grounding Character Identity in Video Captioning and Question Answering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10641", "title": "Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10156", "title": "HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10639", "title": "Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10150", "title": "On the Reliability of LLM-Based Vulnerability Patching Benchmarks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10145", "title": "InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey Interviews", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10141", "title": "AdaT$^2$: Adaptive Test Transformations for Black-Box Boundary Testing of Conversational Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10126", "title": "Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10124", "title": "Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10120", "title": "RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10118", "title": "YANchor-4B: Effective Long-Horizon Reasoning in O(N) Time with O(1) Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10114", "title": "Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10092", "title": "I would rather quit NLP than read another paper like this: The rise of antithesis in NLP papers", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10091", "title": "ExperienceIndex: Artifact-Grounded Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10071", "title": "HGP:An on-device personalized agent memory via hybrid graph storage", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10068", "title": "Efficient Provably Private Classification with a Tabular Foundation Model", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10066", "title": "From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10062", "title": "Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10061", "title": "TRACK: Telemetry-Based Racing Analysis and Coaching Kit in Sim Racing Games", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10058", "title": "Cache the Encoder Within:Compact, Reusable Memory across LLM Queries", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10633", "title": "Has LLM Screening Performance Stalled in Software Engineering Systematic Reviews?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10042", "title": "Learning to Accumulate Knowledge with Mutual Information", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09995", "title": "Designing Collaborative AI-Driven Workflows for Scientific Software Engineering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09985", "title": "Marrying Pricing and Advertising with LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09973", "title": "From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09969", "title": "TR-PTQ: High-Accuracy Integer-Only Transformer Post Training Quantization via Taylor Region Reformulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10629", "title": "The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09952", "title": "MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake Detection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09941", "title": "Purifying Backdoored Large Vision-Language Models by Removing Hijacked Directions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09940", "title": "Juno: Taming Predictive Latents for Vision-Language-Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09935", "title": "AgentTracer: Tracing Indirect Prompt Injection Attack through Fine-Grained Intention-Execution Alignment", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09934", "title": "Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09920", "title": "Inverting Multi-Vector Visual Document Indices", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09919", "title": "Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its Breaking", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09914", "title": "RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09907", "title": "FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09906", "title": "Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09872", "title": "LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09870", "title": "Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10628", "title": "Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09858", "title": "Training Advisors for LLM Agents from Task Outcomes", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09856", "title": "Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09841", "title": "ORCA: Hunting Compositional Failures in Text-to-Image Diffusion", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09835", "title": "A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09832", "title": "SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09824", "title": "Homogenization in Multi-Agent Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09823", "title": "UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09804", "title": "BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09802", "title": "DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09795", "title": "MIRROR: From Imitation to Internalization in LLM Personalization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09788", "title": "Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09772", "title": "Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09769", "title": "Bolzano: From Expert-Guided Proof Search to Automated Open-Problem Solving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09763", "title": "Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09761", "title": "PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09746", "title": "Flow-of-Thought: A Framework for Visual Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09742", "title": "SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09718", "title": "YUBI-STAG: Contact and Semantic-Rich Alignment for VLAs via Automated Video-Language Grounding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09710", "title": "SpikingVLA: Asynchronous Spiking Vision-Language-Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09703", "title": "Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09700", "title": "What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10623", "title": "Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10622", "title": "WorldBench: Evaluating LLMs on Three.js Voxel World Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09684", "title": "From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09683", "title": "System Switch: When Should a Fast Decision Model Stop and Think?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09681", "title": "Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09665", "title": "SAPD: Step-Aligned Privileged Distillation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09647", "title": "When Rank Rises as LLMs Degrade", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09643", "title": "CircuitATLAS: Agentic reasoning over a systems neuroscience knowledge graph for target discovery in circuitopathies", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09639", "title": "On-Policy Distillation Teaches New Skills but Not New Knowledge", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09633", "title": "Coding-Agent Benchmarks Should Match Their Users' Task Flows", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09624", "title": "How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10619", "title": "TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09597", "title": "COPC: Coupled Off-Policy Correction for Asynchronous LLM Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09590", "title": "Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09587", "title": "Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10616", "title": "When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09581", "title": "Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10612", "title": "PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09563", "title": "EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09550", "title": "Visual Evidence Under Cross-Examination: Evaluating and Controlling Decision-Level Evidence Use in Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10610", "title": "Code Understanding is a Bottleneck for Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09517", "title": "It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09514", "title": "STRIKE: Learning Visual State Transitions for Physical World Modeling", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09513", "title": "OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09496", "title": "Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09489", "title": "Goldsmith: Gold-Loss-Guided Definition Optimization with an Agentic Annotation Harness", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09484", "title": "MIMESIS: Learning User Simulators as Training Environments for Interactive Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09478", "title": "InstanceBench: Diagnosing Referential Reasoning and Target Identity in Referring Expression Segmentation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09476", "title": "CHASE: Channel-Aligned Structure Exploitation for Geometry-Aware Model Engineering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09471", "title": "When Should an In-Context Learner Expand Its Hypothesis Space?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09467", "title": "Boundary-Free Contextual Biasing: Depth-Adaptive Gating and Reading-Space Matching for Unsegmented Languages", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09466", "title": "LLM-Enabled UAV Dispatch: A System-Level Survey and Taxonomy", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09457", "title": "DSReg: Provably Recovering Individual World Latents without Reconstruction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09440", "title": "Mixture of Layers: Dynamic Layer Routing for Visual Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09430", "title": "SkillCycle: Co-Evolving Agent Policies and Skill Banks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09408", "title": "TiTok: Audio-Visual LLM for Multi-Segment Temporal Grounding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09400", "title": "TutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative Feedback", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09392", "title": "Quantifying Volumetric Risk: Class-Aware Asymmetric Weighted Conformal Prediction for 3D Medical Image Segmentation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09384", "title": "The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09375", "title": "From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer Analysis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09374", "title": "DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09371", "title": "The Confidence Game: Strategic Miscalibration in Human-AI Delegation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10608", "title": "From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09360", "title": "TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09355", "title": "Multimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG Decoding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09348", "title": "Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09346", "title": "OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09342", "title": "Shared Low-rank Basis Factorization for Data-free Mixture-of-Experts Compression", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09337", "title": "Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09328", "title": "Visual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10604", "title": "Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09313", "title": "Why VLMs Miss Small Objects, and When Zooming In Is Safe", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09311", "title": "Denoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token Realization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09296", "title": "The AI Evaluation Ecosystem", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09267", "title": "Who Broke Me? Execution-Guided Repair of Behavioral Dependency Breaks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09264", "title": "Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09252", "title": "Adaptive Visual Token Reduction for Accelerated Image Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09247", "title": "An Informational Curse of Horizon in Goal-Conditioned Policy Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09243", "title": "We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09240", "title": "Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09227", "title": "Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text Embedders", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09219", "title": "CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09218", "title": "RLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09217", "title": "A Deterministic Evidence Layer for Vision-Language Autism Screening from Naturalistic Home Video", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09209", "title": "Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09205", "title": "Do Vision Models Learn Physical Constraints or Rendering Shortcuts? A Counterfactual Benchmark for Grounded Physical Consistency", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09202", "title": "Few Bits, One Law: Toward W2A4KV2", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09193", "title": "Bookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09186", "title": "The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09179", "title": "LayerRoPE: Dynamic Depth-wise Magnitude & Angular Superposition", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09163", "title": "ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09159", "title": "SpecGuard: Proving a Task Is Broken Before the Agent Cheats", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09152", "title": "sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09142", "title": "Finding Blind Spots in AppWorld and WorkArena Task Verifiers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09141", "title": "A Cognitive-Aware QML-CRL Framework for Detecting Affinity and Romance-Investment Fraud", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09139", "title": "Breaking the Space Barrier and its Application to Language Model Inference", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09127", "title": "CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09120", "title": "The Deceptive Bandit Problem: Exploratory Coupling and the Fragility of Multi-Agent Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09115", "title": "From Uncertainty to Action: Learning to Steer LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09112", "title": "GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09096", "title": "Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09085", "title": "Anaximander: Interactively Running Geospatial Deep Learning Models on Any Compute Backend", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09079", "title": "Large-scale Repository Engineering via Agent-Native Reusable Code Primitives", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09074", "title": "TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09070", "title": "Covariate-dependent Joint Modeling of Multivariate Ordinal Preferences and Its Connections with Comparison Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09063", "title": "Multi-Label Topic Assignment via LLM Distillation: A Comparative Analysis of Generative vs. Discriminative Student Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09053", "title": "Justice After Identity: Large Language Models and the View from Everywhere", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09051", "title": "A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09027", "title": "Visual Memory Attacks Can Persist Through The KV Cache", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09021", "title": "Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09015", "title": "Personalize at Test Time: Learning User Preferences for Image Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09008", "title": "Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09003", "title": "Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09000", "title": "How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10592", "title": "Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08963", "title": "On KL-Regularized Policy Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08959", "title": "GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08954", "title": "RACER: Reflective Agent Coupling Query Interpretation and Tool-Based Retrieval for Frame Selection in Long Video Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08941", "title": "SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08928", "title": "Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08917", "title": "CARE: Certifying Acceleration for Vision-Language-Action Inference", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08791", "title": "World Models' Last Exam in Physics", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08779", "title": "ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08901", "title": "Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08775", "title": "Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08720", "title": "WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08718", "title": "When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08713", "title": "SpaTime: Streaming Vision-Language Models for Spatio-temporal Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08691", "title": "ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08678", "title": "Secure Speculative Decoding for Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08674", "title": "EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08668", "title": "Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08662", "title": "ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08659", "title": "Selective Transfer of RL Updates for Visual Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08651", "title": "A Case Study in Assuring AI-Written Software", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08649", "title": "Stable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice Evaluation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08647", "title": "SquidAgent: Parallelize Wisely, Coordinate Efficiently", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08639", "title": "Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08630", "title": "Towards In-Parameter Memory Augmentation for Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08622", "title": "Agentic RCA for Internet-Scale Services Using Constrained Creativity", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08621", "title": "Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08586", "title": "MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08560", "title": "Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08539", "title": "RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08528", "title": "MedCORE: Criteria-Grounded Clinical Reasoning for Interpretable Medical Image Diagnosis", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08526", "title": "WareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart Warehouses", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08514", "title": "How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08513", "title": "Wiki-Talkie: Multilingual Benchmarking of Persona-Based Agents on Real-World Discussions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08482", "title": "Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08463", "title": "UNREAL: Unifying Retrieval and Long-Context with a Single Model", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08452", "title": "Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08430", "title": "NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08414", "title": "Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08407", "title": "Seeing the Context: Enhancing Recommender Systems with Image-Derived Contextual Signals", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08403", "title": "SSR: Sparse Segment Reduction for Ternary GEMM Acceleration", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08401", "title": "GeoPID: Decomposing and Steering Visual Information in Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08400", "title": "Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08364", "title": "Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08341", "title": "DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08337", "title": "Machine Learning for German Redispatch Forecasting under Data Delays and Temporal Distribution Shift", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08331", "title": "Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08327", "title": "MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08300", "title": "Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08250", "title": "MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08246", "title": "LeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08245", "title": "Aligning Performance with Contribution: Towards Contribution-Aware Fair Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08232", "title": "Behavior-Mining, Generative Conversations, and Collaborative Advisory: the Future of Travel and Tourism Recommender Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08215", "title": "Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08208", "title": "STRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficulty", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08200", "title": "Finding the Heads and the Neurons Responsible for Network Information Retrieval in Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08183", "title": "Compact Robot Policies Need Fine-Grained Visual Representations", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08164", "title": "Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08162", "title": "The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08159", "title": "Making COMET Comparable Across Scripts: Diagnosis and Correction of Tokeniser-Induced Script Bias in Indic MT Evaluation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08155", "title": "Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08136", "title": "Adapting Generative Recommenders for Multi-Turn Interaction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08133", "title": "VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08129", "title": "Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08106", "title": "ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08101", "title": "Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08097", "title": "When Tools Lie: Reliability of Mathematical Agents Under Corrupted Tool Feedback", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08090", "title": "Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08076", "title": "SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08068", "title": "PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08048", "title": "DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08881", "title": "Mitigating Uncertainty Interactions in GenAI-based Adaptive Systems: Vision, Challenges and Preliminary Guidelines", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08018", "title": "Structured but Silent: Probing Capability Requirements in LLM Hidden States", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07990", "title": "A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07987", "title": "VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07982", "title": "M3SunAgent: Monocular 3D Spatial Understanding Agent for Metric Depth Estimation and 3D Visual Grounding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07972", "title": "Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07969", "title": "EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07966", "title": "Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and Distribution", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07954", "title": "Revisiting Numerical Forecasting Models for Language-Based Trajectory Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07948", "title": "Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07940", "title": "Hybrid Latent Attention for Looped Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07937", "title": "Leveraging a four-quadrant approach for evaluating Redpine Science", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07935", "title": "SIGMA: Self-Improving Alignment Generalization from a Model Spec", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07925", "title": "TF-PRVR: Training-Free Partially Relevant Video Retrieval", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07913", "title": "Multimodal Knowledge Distillation for Gastric Adenocarcinoma Classification from Whole-Slide Images", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07903", "title": "Unsupervised Long-Tailed Adaptation of Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07887", "title": "Visual Abstention in Unified Multimodal Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07886", "title": "ShanLiangRen: A Nutrition Agent for Personalized Daily Meal Planning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08879", "title": "Tiny-Scale Chinese BERT Pretraining: A Controlled Comparison of MLM, WWM, and MacBERT Strategies", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07881", "title": "Self-Referenced Social Preferences: Cooperation without Observing Others Rewards", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07868", "title": "CueRator: Agentic Search for Symbolic Rules to Adapt Frozen Multimodal Encoders", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07863", "title": "ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07862", "title": "A self-learning scientific agent for X-ray diffraction", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07860", "title": "WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestration", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07851", "title": "RA-MoWE: Workflow-Affinity Embeddings for Query Clustering and Agentic Workflow Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07848", "title": "Dynamic Positional Attention Modulation for Parameter-Efficient Fine-Tuning of Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07835", "title": "DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07832", "title": "Harness Engineering for Software Engineering via Modular Executable Dev-Primitives", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07825", "title": "Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07819", "title": "$α$Transfer: Coefficient Transfer for Efficient Model Merging", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07817", "title": "One Step at a Time: Trading LLM Autonomy for Process Predictability", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07816", "title": "Do I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07810", "title": "SIFT: Search Intent-to-Filter Transformer for Multi-Task Personalized Filter Ranking at Airbnb", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08875", "title": "An Empirical Study of Agent Skills' Downstream Utility", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07809", "title": "MASKerade: Token-Routed Mask Experts for Dense-to-MoE Upcycling", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07787", "title": "OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07782", "title": "Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07774", "title": "Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08871", "title": "CredLeakBench: Evaluating Credential Leakage and Recovery in LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07763", "title": "ST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research Tasks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07761", "title": "Contrastive Learning for Aspect Representation towards Explainable Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07758", "title": "Later Is Better: Token Reduction for ViTs Under Distribution Shift", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07757", "title": "Acquiring and Verifying Repository Norms for Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07755", "title": "Trustworthy Method Comparison with AI Judges: Estimation and Design under Order, Batch, and Aggregation Effects", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07753", "title": "From Evidence to Action: How Tool-Using Agents Fail", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07751", "title": "How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07729", "title": "Foveated Compression: Selective High-Resolution Preservation for Token-Efficient VLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07706", "title": "WASD: Wasserstein-based Knowledge Distillation for Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07704", "title": "Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07689", "title": "Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10580", "title": "A Survey on LLM-Integrated Hardware Design Verification", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07668", "title": "CACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07657", "title": "Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07645", "title": "SkillPoison: Progressive Skill Poisoning via Successful Experiences", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07643", "title": "Monte Carlo Estimation for KV Cache Eviction", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07640", "title": "Towards the Automatic Synthesis of Interpretable Chess Tactics", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07639", "title": "HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07625", "title": "Stateless Language Agents: Scaling Long-Horizon Automated Research", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07615", "title": "AFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget Constraints", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07594", "title": "BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07588", "title": "Personal-Agent Mediated Recommendation with Cross-Platform User History", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07585", "title": "REViT-v2: Hierarchical Windowed Roto-reflection Equivariant ViT for Equivariant Feature Extraction", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07578", "title": "Cooperating with Future Collaborators: Multi-Agent RL under Staggered Participation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07576", "title": "CETUS: How Far Do Representations Trained on Earth Transfer to Cassini SAR of Titan?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07572", "title": "Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07570", "title": "Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Forms", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07569", "title": "OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07557", "title": "CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07556", "title": "Decoupled Multi-Agent Orchestration", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07553", "title": "Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07550", "title": "Foundation Model-Aided Multi-Agent Reinforcement Learning for Wireless Random Access Network Optimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07535", "title": "Disentangling Models from Personas in Heterogeneous LLM Simulations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07534", "title": "The EPIC Framework for Spec-Driven Development", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07533", "title": "SkillFormer: Skill-Decomposed Adaptation for Audio Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07532", "title": "Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07522", "title": "Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07509", "title": "On Open-Ended Information Seeking for Information Elicitation Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07491", "title": "Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07489", "title": "Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07475", "title": "Adapting to Changes in Agent Behavior via Finite-Depth Policy Sensitivity", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07473", "title": "PsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07460", "title": "ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07457", "title": "AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07426", "title": "AccentCL: Robust Accent Classification with Incremental Expansion", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07423", "title": "2d-fet-bench: from spatial reasoning to fet design on flakes", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07402", "title": "Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07389", "title": "Inference and learning in sparse autoencoders as natural gradient flow", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07385", "title": "Semantic Capability Acquisition and Specialization During Vision-Language Model Fine-Tuning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07376", "title": "MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07359", "title": "Evaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07355", "title": "Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07349", "title": "RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07348", "title": "Stepped MoE: Segment-Level Routing with Configurable Inference Complexity", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07339", "title": "A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07338", "title": "Logbook: Extremely Long-form Audio Event Understanding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07335", "title": "Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07332", "title": "Structuring MoE Expert Selection for Agentic Reinforcement Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07324", "title": "Scale-Invariant Training for Time Series Foundation Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07311", "title": "Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07289", "title": "Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07269", "title": "What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07261", "title": "Verifying Coordination in Parallel Coding Agents: NP-Bench and a Scheduling Planner", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07258", "title": "Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07243", "title": "Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07191", "title": "Agentic Design Space Exploration for Joint Hardware Configuration Selection and Mapping of AI Inference Workloads on Heterogeneous Edge SoCs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07168", "title": "A theory of platonic representations in language models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07132", "title": "CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06844", "title": "Learning to Read the Contextual Tokens in Diffusion Transformers", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06843", "title": "Recursive Video In-Context Learning for Agentic Robot", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06830", "title": "MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06825", "title": "PlotGround: Grounding Plot Digitization in Real Scientific Figures and Their Source Data", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06817", "title": "Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07127", "title": "PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06790", "title": "Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06784", "title": "How to scale your HEP ML models: A recipe for robust architecture comparisons at scale", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07121", "title": "SoloQ: Calibration-Free Quantization for Diffusion Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06751", "title": "MatrixFormer: A Foundation Model for Matrix Completion", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06750", "title": "Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06748", "title": "BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06726", "title": "Decoupling Time and Space: A Temporally Conditioned Refinement for EEG Source Imaging", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07118", "title": "AMBER: Training Long-Horizon Web Agents through Append-Only Memory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06715", "title": "Domain adaptation of Russian ModernBERT for long legal documents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06703", "title": "Reading the Mood: Emotion-Guided Book-to-Music Recommendation via CGANs and LLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06695", "title": "MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA Tasks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06686", "title": "OVAL: Output-Aware Local Page Bases for KV Cache Retrieval", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06685", "title": "Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06670", "title": "Reward Stealing Attack on Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06666", "title": "What Matters for Latent Reasoning with Flow Matching", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06651", "title": "Considering Context: When World Models Need Context Encoders", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06650", "title": "Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06647", "title": "LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06636", "title": "Differentially Private Mixing of Public Datasets Improves Private Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06617", "title": "RealtimeWAM: One-Step Asynchronous World Action Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06616", "title": "Video Encoders Built on Image Representations", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06614", "title": "FREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06611", "title": "Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06603", "title": "Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06598", "title": "SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06597", "title": "Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06590", "title": "SPRIG: Semantic-ID-enhanced Paths for Knowledge Graph-based Generative Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06584", "title": "Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06582", "title": "Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06576", "title": "Before Agent Tells The Lie: Has Deception Already Been Represented?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06571", "title": "BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06563", "title": "HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06514", "title": "ANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior Auditing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06479", "title": "Behavior-Preserving KV Cache Compression", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07105", "title": "Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06454", "title": "AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06446", "title": "The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06413", "title": "SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06411", "title": "From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06409", "title": "FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06406", "title": "What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06404", "title": "Quantifying the Stability of Multi-Step Reasoning via Error Amplification", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06401", "title": "RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06394", "title": "Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06387", "title": "Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06324", "title": "Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06320", "title": "CRAFTER: Causality-based Self-adaptation for Autonomous IoT Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07091", "title": "Smart Content Ingestion for Generative AI Workloads", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06293", "title": "VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06286", "title": "DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06269", "title": "Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07089", "title": "Towards a Unified Misuse Monitoring Benchmark", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06251", "title": "Shared Stopping Decisions Change Answers in HQQ Cache Quantization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06226", "title": "LeAVJEPA: A Minimalist Architecture for Audio-Visual Self-Supervised Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07086", "title": "SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06207", "title": "AI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06204", "title": "Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06196", "title": "EORestore-Agent: Fidelity-Guided Agentic Restoration of Remote Sensing Images with Composite Degradations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06193", "title": "Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06192", "title": "Copies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent Systems", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06191", "title": "Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06190", "title": "Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06163", "title": "Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06161", "title": "Introducing Code-Switched Contexts to Cognitively-Inspired Bilingual Model Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06148", "title": "Reinforcement Learning-Based Optimization of Workload-Aware Power Delivery Networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06147", "title": "Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06122", "title": "Benchmarking Jailbreak Guardrails for Embodied Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06100", "title": "From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06083", "title": "Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06069", "title": "Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06064", "title": "TrustMI: Causally controlling how assistants trust their users", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06063", "title": "Vision Transformer Ensembles for Panoramic Street Segmentation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06056", "title": "ROT: Rotating Hidden States towards Contextual Vectors for Hallucination Mitigation in LVLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06050", "title": "MATE: Adaptive Long- and Short-Term User Memory for LLM-Based Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06047", "title": "Let the Agent Do It? How Software Practitioners Understand and Make Permission Decisions in Agentic AI Assistants", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06039", "title": "MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06026", "title": "Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06025", "title": "Grounded Joint-Attention Other-Play for Zero-Shot Coordination", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06021", "title": "Scalable Minimal-Change Learning for Controllable Image Editing", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06019", "title": "Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06018", "title": "Investigating Query-Insensitive Behavior in Spatio-Temporal Video Grounding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08858", "title": "LRCC: Generalizing Low-Rank Compression with Conditional Computation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06001", "title": "AgentSpy: Making AI Agent Behavior Observable", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05994", "title": "How (and How Not) to Use Data Augmentation in VLA Post-Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05993", "title": "From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image Retrieval", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05982", "title": "Breaking the Tie: A Cluster-Aware Routing Framework for Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05981", "title": "Mechanizing the User's Eye: Pre-Registered Deployment of a Sabotage-Validated Fail-Plausible Observer in a Production LLM Agent Runtime", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05978", "title": "Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05961", "title": "Strategic Multi-Agent Learning for Interpretable Action Valuation of All Players in Football", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05949", "title": "Technical Report on the Turba Fertilizer Machine Learning Stack in Morocco", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05940", "title": "ReMem: Streaming Video Understanding With Long Context Retention", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05897", "title": "Fitting Vision Adapters at Frontier Scales", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05896", "title": "TasteRoute: Personalized Routing for Video Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05885", "title": "The Optimization Landscape of Learning Compacted Context Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07062", "title": "Learning to Simulate Individuals from Macro Social Signals", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05879", "title": "Learning to Learn a Language", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05874", "title": "Global Communication or Graph-Specific Memory?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05872", "title": "Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07060", "title": "Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05863", "title": "CCQ: A Multi-State Child Care Quality Dataset to Support AI for Children's Health Research", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05861", "title": "Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05842", "title": "HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05833", "title": "Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05828", "title": "Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05787", "title": "Constraint-Aware Conversational Job Recommendation in Code-Mixed Low-Resource Settings", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05778", "title": "MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05774", "title": "AdaSpark: Adaptive DSpark with Online Learning for Tree Verification and N-gram Fill", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05750", "title": "Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05744", "title": "CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05715", "title": "Rotated, but How Far? Diagnosing and Improving Object-Rotation Reasoning in VLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05709", "title": "Nexus: An Execution Fabric for AI Agents Across Cloud, Edge, and Devices", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05697", "title": "From Token-Max to Outcome-Max: How You Use AI Determines Its Productivity", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05690", "title": "Errors of LLM-Assisted Literature Retrieval in Environmental Science: A Comparison Study of Abstract versus Full-text Based Prompts", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05685", "title": "Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05681", "title": "Automatic Speech Recognition for Low-Resource Sinhala: A Critical Review of Methods, Challenges, and Future Directions", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05670", "title": "Generate What You Can Trust: Content Credibility in Generative Recommenders", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05664", "title": "StageVLN: Spatial and Trajectory Auxiliary Guidance for Efficient Vision-Language Navigation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05637", "title": "Visual Grounding Safety in Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05630", "title": "Atomic Visual Entailment: Enhancing Zero-Shot Vision-Language Reasoning through Atomic Fact Decomposition and Learned Selection", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05622", "title": "UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05615", "title": "DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05591", "title": "What Is a Repeated Token Worth? The Scaling Geometry of Multi-Epoch Pretraining", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05586", "title": "AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05572", "title": "Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05569", "title": "Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05563", "title": "G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05559", "title": "Cut Binary Cross Entropy: Efficient Large-Vocabulary Loss and Gradient Kernels for Sequential Recommendation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05540", "title": "SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05538", "title": "LiFT: Loop Flow Transformers", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05532", "title": "DelegationBench: Measuring When AI Agents Should Ask Before Acting", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05501", "title": "Logic-Logit: A Logic-Based Approach to Choice Modeling", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05484", "title": "Universal Test-Time Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05473", "title": "Hierarchical Reinforcement Learning with Stable Temporal Abstraction for Language Model Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05463", "title": "Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05461", "title": "AI Safety via Debate is Compromised by Cognitive Biases", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07032", "title": "Investigating Model Compression for Neural Machine Translation in the Biomedical Domain", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05425", "title": "Unmentioned Checklist Findings Change How Reinforcement Learning Appears to Improve Chest Radiograph Report Checking", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05418", "title": "EvoMem-VLA: State-Evolution Memory for Long-Horizon Robot Manipulation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05417", "title": "Render to Reason: Novel-View Semantic Prediction Improves Spatial Understanding in VLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05413", "title": "A Strong Baseline for Evaluating Vision Encoders in Multimodal Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05402", "title": "Task Vector Descent: Learning from Non-IID Batches", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05400", "title": "CASE: Cost-Aware Stopping for Efficient Long-Video Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05399", "title": "Adaptive Code Revision Attacks on AI Pull Request Reviewers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05398", "title": "MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05387", "title": "GNN-CB: A Graph Neural Network Competition Benchmark for Human and LLM Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05383", "title": "Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05380", "title": "VHDL-REPOBENCH: A Repository-Level Benchmark for Evaluating Large Language Models on VHDL Design Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05369", "title": "AutoDP-LLM: Automating Data Pre-processing for Intrusion Detection Systems using Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05342", "title": "IRSTD-Agent: Agentic Infrared Small Target Detection via Zoom-Guided Interaction Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05334", "title": "AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05319", "title": "Understanding the Hierarchical Structure and Functional Landscape of the Model Context Protocol Ecosystem", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05318", "title": "Robust Parameter-Efficient LLM Adaptation on Analog Hardware", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05306", "title": "Kinematics-Centric Continuous Sign Language Retrieval with Gloss-Guided Boundary-Aware Alignment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05305", "title": "Characterizing Parallelism Strategies in LLM Inference: Fundamental Compute-Communication Trade-offs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05303", "title": "ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05300", "title": "MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05295", "title": "Readable Before Actionable: Causal Tracing of Indirect Prompt Injection", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05292", "title": "Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05284", "title": "Fusion is the New Mutation: Bandit-Guided Evolution on Workflow Graphs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05274", "title": "Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05273", "title": "When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05249", "title": "ArticuTable: Generating Instance-Level Interactive Rigid-Articulated 3D Tabletop Scenes from a Single Image", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05247", "title": "templar: agentic induction and evolution of standardized radiology reporting templates from large-scale clinical corpora", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05241", "title": "StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07014", "title": "DTFormer: Text-Guided Semantic Alignment for RGB-D Segmentation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05223", "title": "Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05220", "title": "Ranking Bandits for Carousel Interfaces with Observable Browsing Depth", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05219", "title": "Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05190", "title": "FORGE: Verification-Gated Behavioral Repair for Generative Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05185", "title": "Recurrent Latent Visual Search for GUI Grounding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05176", "title": "AECG: Asymmetric Experience Consolidation and Governance In Multi-Agent Systems", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05162", "title": "Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05132", "title": "SpecAgent: Empowering Program Verification with Agentic Synthesis of Formal Program Specifications", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05131", "title": "RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05129", "title": "Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05126", "title": "Selecting Repetition Counts Across Model Scales in Data-Constrained Pretraining", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05124", "title": "Memory Canonicalization: A Framework and Benchmark for Cross-Model Drift in Persistent LLM Memory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05119", "title": "LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05114", "title": "Belief-Trajectory Energy: Measuring the Path to a Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05111", "title": "InstMoE: Adaptive Multimodal Routing with Specialized Experts", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05107", "title": "SearchJev: A Fast and Calibrated System-1 Model for Search Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07004", "title": "Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05103", "title": "VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05100", "title": "METRO: Metric-Enhanced Token Routing Operator", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05097", "title": "ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05066", "title": "Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05047", "title": "Beyond Task Completion: Measuring Interaction Cost in Terminal User Interfaces", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05041", "title": "Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05039", "title": "Causal Improvement Graph for Agentic Harness Optimization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05037", "title": "SparseCraft: Agentic Hardware-Software Co-Optimization for Sparse Computing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05036", "title": "Characterizing Security Effects of OSS Vulnerabilities in Agent Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05030", "title": "EVISKILL: Grounding Skill Evolution in Replayable Evidence", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05029", "title": "SPACE-CLIPv2: Decoding Local Geometry from Frozen CLIP for Monocular Depth Estimation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05026", "title": "GeoBridge-VLA: Geometry-Aware Residual Adaptation for Vision-Language-Action Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06993", "title": "DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05025", "title": "Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05024", "title": "LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05023", "title": "Look Where You Say You're Looking: Self-Grounded Attention for Visual Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05009", "title": "Rethinking Tool Design for Agentic RCA: A Controlled Empirical Study", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04991", "title": "CIPO: Counterfactual Imagination Policy Optimization for Adaptive Tool Granularity Selection", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04977", "title": "Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04976", "title": "Priced Guidance: Can Language Models Generate Future Research Ideas?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04973", "title": "TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04961", "title": "Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04957", "title": "Trinity: One Differentiable Physics for Training, Refining and Scoring Generative Floorplanners", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04940", "title": "Software World Models: From Consequence Prediction to Decision Value", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04927", "title": "Assembling Insights for Agentic Machine Learning Engineering Systems", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04921", "title": "Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04918", "title": "Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04916", "title": "PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04915", "title": "Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04893", "title": "SFlexRCA: Lightweight, Scalable, and Flexible Root Cause Analysis for IIoT Edge Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04889", "title": "ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04878", "title": "Bounded Reasoning: Cognitive Hierarchy in Human-versus-AI Cyber Defense", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04868", "title": "From Memory to Guide: Spatio-Temporal Composer for Procedural Coding Memory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04867", "title": "Greedy Local Learning for Language Model Pretraining: Gaps and Objective Design", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04862", "title": "GitSwarm: Decentralized Compounding Inference", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04832", "title": "Agent Skill Evolution: How Revisions Affect Coding Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06977", "title": "Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04824", "title": "Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04805", "title": "ExStereo: Lifting 2D Vision-Language-Action Models to 3D with Explicit Stereo Representations", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04802", "title": "Multi-Agent Spectrum Sharing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04794", "title": "Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04792", "title": "Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04779", "title": "Asymmetric Repository Lineage Modeling and Verifier-Guided Coordination in Concurrent AI Coding Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04777", "title": "ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04753", "title": "More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06972", "title": "BoT-Feedback: Grounding Multimodal Reasoning in Biomechanical Evidence for Explainable Human Action Feedback", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04740", "title": "Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04721", "title": "Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06971", "title": "AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04716", "title": "Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04699", "title": "Not Self-Decidable: LLMs Cannot Draw the Boundary of What an Agent Verifier Can Check", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04687", "title": "Understanding Errors in LLM-Based Question Answering over Imperfect Tables", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06966", "title": "APEX: Active Protection at Execution Boundaries for LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04672", "title": "MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06964", "title": "Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04658", "title": "RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06963", "title": "WavePrune: One period is often enough for RoPE", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04651", "title": "GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04646", "title": "SEIS: Self-Evolving Inference Systems", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04641", "title": "Back to the Future: Regressing Readability Features from LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04639", "title": "When Talk Isn't Code: Comparing LLM Agents That Simulate and Develop Software", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04636", "title": "Does Neural Complexity Improve Health Misinformation Detection? A Leakage-Controlled Cross-Corpus Benchmark", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04616", "title": "PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04611", "title": "Practical Runtime Enforcement of First-Order Temporal Requirements", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04607", "title": "ForeAct3D: Policy-Grounded Future World Modeling for VLA Policies", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04589", "title": "StegoMemory: Agentic Memory Acts as Covert Steganographic Channel", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04580", "title": "Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04575", "title": "From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04569", "title": "From Transformers to Weighted Automata: Towards the Verification of Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04555", "title": "$\\mathrm{TRIZ}^{a}$: Guiding Agent Evolution from Pattern Recognition to Solution Invention", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04544", "title": "Label Agreement Does Not Measure Authorization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04541", "title": "Autonomous Structuring of Radiology Reports Across Modalities at Archive Scale Using an Open-Weight Large Language Model", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04528", "title": "Quantifying Collusion Among Autonomous LLM Agents: A Statistical Analysis of the Collusion Wiki Incident", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04518", "title": "Length Generalization Needs Proper Regularization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04517", "title": "EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04512", "title": "Correctness Is a Direction: Geometric Answer Selection in Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04507", "title": "LoRA's Second Descent Extends Beyond Parameter Parity", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04506", "title": "EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04504", "title": "The Same Zero: Why Identical ASR Can Imply Different Guarantees in LLM-Agent Security", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04502", "title": "Localization Lens for Improving Medical Vision-Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06950", "title": "Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04499", "title": "Homogeneous Semantic Alignment and Hierarchical Expert Routing for Radiology Report Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04494", "title": "DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04488", "title": "Can LLM Agents Automate Reinforcement Learning for Text-to-Speech?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06949", "title": "AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04433", "title": "What Does a Harness Buy? Tokens, Mostly", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04432", "title": "Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04429", "title": "Asking Earns Nothing: Scoring the Decision to Act in BFCL Multi-Turn", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04425", "title": "AgroGround: Multi-Granularity Grounded Recognition in Agriculture", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04424", "title": "On the Trade-off Between Information Loss and Generalization in Sparse Attention", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04418", "title": "CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04413", "title": "Specific Algorithmic Interpretability of Neural Networks: A Case Study on Textures", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04409", "title": "Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04403", "title": "Saying, Not Knowing: Aggressively GGUF-Quantized Small Language Models Still Write Rare Words They Can No Longer Define", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04381", "title": "Beyond Plausibility: Verifiable Fine-Grained Image Editing on Structured Assets", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04379", "title": "AgentPersonaBench: Benchmarking Persona-Driven User Simulation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04378", "title": "COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04375", "title": "Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04371", "title": "Functionally Equivalent or Not? Graph-Grounded Differential Surrogate Execution for Code Equivalence", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04366", "title": "Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04318", "title": "Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04303", "title": "What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04302", "title": "From Valid to Useful: Post-Verification Acquisition for Recursive Self-Improving Recommendation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04292", "title": "LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04278", "title": "Do RUL explanations hold up? Faithfulness and stability of attributions on C-MAPSS", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04263", "title": "Multimodal Dual-Encoder Retrieval for Automated ICD Coding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04255", "title": "Grounded in Time: A Multi-Source Dataset and Benchmark for Temporal Grounding in Robotic Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04246", "title": "Benchmarking Psychological Dynamics in Generative Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04225", "title": "FlashGaze: Training-Free Multi-Scale Patch Pruning For Efficient Video Understanding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06932", "title": "RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04204", "title": "Clean: Second-order LLM Training at Linear Memory Cost via Nyström Sketching", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04196", "title": "Asynchronous Is Nearly Free for Evolution Strategies on Long-Horizon Agentic Tasks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04178", "title": "SHarP: Saliency-based Pruning of Agent Harnesses", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04168", "title": "Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04156", "title": "Trajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04152", "title": "Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04140", "title": "ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04139", "title": "From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04138", "title": "Dual-Scale Relational Graph Transformers for Ecosystem-Aware Fraud Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04134", "title": "Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04133", "title": "Auditing Pairwise Equivalence Judgments: Self-Critique Effects and Diversity Measurement in Multi-Agent Hypothesis Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04125", "title": "Representational Control over Self-Report & Behavior Coherence in LLM Risk-Taking", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04118", "title": "LongSocialBench: Do Long-Context LLMs Understand Online Discussion Threads?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06923", "title": "RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04104", "title": "Where Does the Semantic Gain Come From? A Reproduction and Extension of Semantic Knowledge-driven Contrastive Learning for Long-Tailed Recognition", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04083", "title": "Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04053", "title": "The Cost of a Hop: Benchmarking NLIP and A2A", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06918", "title": "Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04047", "title": "Periscope: Extending Frozen Language Models Beyond Their Context Window", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04040", "title": "Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04009", "title": "SUAVE: Unified Video-Action Models via Masked Diffusion", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04008", "title": "SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04002", "title": "Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03994", "title": "Solving VeriContest with a Lean-Backed Rust Verifier", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03972", "title": "Probabilistic Algorithms for Ising Machines from Optimization to Generative AI", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03969", "title": "How Do Coding Agents Optimize Software and Report Performance Validation? A Large-Scale Empirical Study of Open-Source Pull Requests", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03938", "title": "MLLMs Fail to Refuse when Using Tools Agentically", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03935", "title": "General Decision Models: Benchmarking and Insights Beyond Jev", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03923", "title": "Learning Robust Personalized Prompts for LLM-Driven Sequential Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03902", "title": "When Evidence Changes: Evaluating Memory Repair and Re-reading in Language-Model Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03894", "title": "Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03713", "title": "What Should World Models Forget? Stratified Retention for Continual Adaptation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03695", "title": "Language Models that Play Chess and Explain Their Moves", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03675", "title": "FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "frugalevo", "detail_path": "agent-research/2610.03675-frugalevo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03634", "title": "Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "depgpo", "detail_path": "agent-research/2610.03634-depgpo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03632", "title": "World Embedding Benchmark", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03631", "title": "NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03620", "title": "UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03617", "title": "DEPICT: Scoring Text-to-Image Alignment by Answer Agreement", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03604", "title": "Mastering Atari 2600 Games with Discovered Options", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06910", "title": "GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03598", "title": "When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03591", "title": "HazardWeaver: Scientific Route Selection for Hazard Analysis Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03585", "title": "Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03574", "title": "HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03567", "title": "Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03529", "title": "Divergence controls entropy in distillation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03525", "title": "Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03524", "title": "From Benchmarks to Production: A Text-to-SQL System for Complex Financial Data", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03516", "title": "XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03502", "title": "Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03476", "title": "MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03468", "title": "A Vision-Language Model (VLM)-based Pipeline for End-to-End Procedural Modeling of Field-Grown Maize from Point Clouds", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03463", "title": "Generalization of Transformer-Based Neural Quantum States via In-Context Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03448", "title": "Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03445", "title": "Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03421", "title": "CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03389", "title": "From Patching to Pruning Visual Computation in Vision Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03356", "title": "ReFract: Benchmarking Perspective Awareness in Language Model Agents with Text World Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03324", "title": "To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech Moderation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03315", "title": "Lightweight, Rubric-Guided Trajectory Evaluation for Production AI Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03289", "title": "Architecture-Dependent Fusion Pathways in MLLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03252", "title": "COSMI: COmpositional Synthesis of Multi-object Interactions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03226", "title": "D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03220", "title": "Evolving Hybrid Quantum-Classical Architectures for Image Classification", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03215", "title": "StanceEval 2026: The Second Stance Detection Shared Task", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03213", "title": "Toward SLM-based agentic task-tool intent matching", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03199", "title": "Predicting and Repairing Merge Collapse in Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03198", "title": "KV$^2$: A Self-Refining KV Cache", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03193", "title": "Bridging Research and Practice: A Systematic Evaluation of Generalist and Dermatology-Specific Models in Clinical Skin Lesion Classification", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03187", "title": "Lightweight and Resource-Efficient Perception for Robotic Guide Dogs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03830", "title": "Memory-State Critic for Asymmetric Actor-Critic with Application to Vision-Based Pursuit-Evasion", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03153", "title": "EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03141", "title": "Behavior Pack Optimization for Video MLLM Post-Training", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03136", "title": "Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03135", "title": "Page-EntroKV: Hardware-Aligned, Entropy-Weighted KV-Cache Eviction under Grouped-Query Attention", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03123", "title": "Foresight: planning future perception in streaming VLMs without retraining", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03112", "title": "Building Interpretable Feature Representations for Resume-Vacancy Matching by Distilling Production LLM Signals", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03102", "title": "Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03099", "title": "Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03098", "title": "Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03089", "title": "Securing Computer-Use Agents Against Branch Steering Attacks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03084", "title": "NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03057", "title": "When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model Behavior", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03056", "title": "MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis Verification", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03055", "title": "hacktrace: behavior-supervised detection of reward hacking during code generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03039", "title": "HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03036", "title": "WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03034", "title": "Adaptive Second-Order Solvers for Fast Stochastic Diffusion Sampling", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03033", "title": "When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03025", "title": "Verifiable, Articulable, and Tacit Components of Preference", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03020", "title": "DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03016", "title": "From Expression to Reaction: Role-aware Visual Transfer and Stimulus-guided Reasoning for Interlocutor Emotion Recognition", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03014", "title": "Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03010", "title": "Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03002", "title": "Recursive Self-Improvement in Unified Multimodal Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02994", "title": "Sentry: Learning to Recover from LLM Agent Failures at Test Time", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "sentry", "detail_path": "agent-research/2610.02994-sentry/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02974", "title": "From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02970", "title": "A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02957", "title": "Understanding Trajectory Heterogeneity in Federated World Model Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02952", "title": "GTDD: Generative Test-Driven Development for AI Coding Agents with Adversarial Testing", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02951", "title": "Dynamic Expert Pruning for Multi-Agent Systems", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02928", "title": "Discriminating Fixture Coverage in Agent-Infrastructure Verification Suites", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02925", "title": "Positive-Unlabeled Learning for Agent Safety False Alarm Auditing", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02910", "title": "Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02887", "title": "Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02885", "title": "PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02880", "title": "Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02878", "title": "Evaluating VQA in Vision Language Models using Cooperative Principles", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02876", "title": "Seeing, Saying, but Not Using: From Reportable Spatial Facts to Usable States in Multimodal Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02847", "title": "Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02841", "title": "How Robust Is Multimodal Claim Verification to LLM Rewriting?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02840", "title": "PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02839", "title": "To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02832", "title": "FastOPD: On-Policy Distillation for Lightweight VLA Deployment", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02814", "title": "VeriPy Source-Preserving Verification and Compatibility Checking for Python Components", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03820", "title": "From Requirements to Attack Trees: Grounded LLM Agents for Design-Time Security Review", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02755", "title": "FiberGeoText: A Vision-Language Model for Population- Level Organization of Superficial White Matter", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02740", "title": "Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02718", "title": "Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02713", "title": "WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02710", "title": "Self-Supervised Scaling of Terminal Environments for Scientific Domains", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02702", "title": "Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02697", "title": "GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02687", "title": "Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02683", "title": "RAOA: Alternating-Operator Neural Computation with Programmable Radio Propagation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02670", "title": "LEAP: Learning Efficient Action Proposals For LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02666", "title": "CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02659", "title": "Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02657", "title": "Context-Tower Conversion Preserves Generation While Freezing Retains Knowledge: Low-Budget AR-to-Diffusion Conversion of MoE LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02654", "title": "Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02638", "title": "Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02626", "title": "Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02617", "title": "WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02616", "title": "VERSE: Verified Self-Evolving Optimizer for Agent Harnesses", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02611", "title": "Scale-Recursive Rectified Flows for Few-Step Precipitation Ensembles", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02610", "title": "Seer: Maximum Likelihood Regression for Learning-Speed Curves", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02600", "title": "When History Misleads: Asymmetric Margin Supervision for Instruction-Guided LLM Generative Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02597", "title": "GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02593", "title": "Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02588", "title": "Open-Endedness Bench: Measuring Epistemic Process from Agent Records", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10563", "title": "SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02569", "title": "Pincer: Resource Authorization for Agents using a Digital Twin", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02549", "title": "Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction Tasks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02542", "title": "How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02525", "title": "Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02523", "title": "Hypothesis-guided discovery of cognitive algorithms via program refinement", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02521", "title": "Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02513", "title": "From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02507", "title": "MeshQuery: Agentic Seam Planning for UV Parametrization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02497", "title": "LiteEMG-FM: An Efficient and Deployable Foundation Model for Robust EMG Sensing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02480", "title": "MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02478", "title": "Tropical Reinforcement Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02472", "title": "APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02462", "title": "Capability Scaling-Down Laws for LLM Compression", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02460", "title": "CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02452", "title": "Reinforcement Learning Techniques for the Optimization of Target Polarization in Nuclear Physics Scattering Experiments", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02451", "title": "A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02442", "title": "AI-driven Thermal-aware Data Center Capacity Planning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02432", "title": "Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02425", "title": "Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02404", "title": "Trained Agentic Context Management", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02396", "title": "Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02388", "title": "Octrees as an Explicit 3D Language", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02386", "title": "Social bot detection in the age of ChatGPT: Challenges and opportunities", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02375", "title": "EviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02369", "title": "Automating the Application of HCI Principles: Skills for On-Demand UI Construction, the Human-AI Space to Think, and the Future of HCI", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02361", "title": "SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02351", "title": "DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02349", "title": "MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02344", "title": "Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02330", "title": "Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02323", "title": "World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02320", "title": "DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02204", "title": "Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02202", "title": "ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02199", "title": "TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "taco-optimizer", "detail_path": "foundation-models/2610.02199-taco-optimizer/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/taco-optimizer-a100-20261002.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.02196", "title": "InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02181", "title": "OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02304", "title": "SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02163", "title": "AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "autocompact", "detail_path": "agent-research/2610.02163-autocompact/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02161", "title": "DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02159", "title": "When Do Intrinsic Rewards Lead to Exploration?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02298", "title": "EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02150", "title": "From Knowledge Access to Source Learning: Developing Source-Specific Competence", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02148", "title": "Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "omni-embed-mini", "detail_path": "foundation-models/2610.02148-omni-embed-mini/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02144", "title": "Faynt: Scaling and Optimizing Policies for Competitive Melee", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02142", "title": "Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02117", "title": "Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "where-opd", "detail_path": "post-training/2610.02117-where-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02091", "title": "GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02076", "title": "LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "llm2jev", "detail_path": "foundation-models/2610.02076-llm2jev/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02074", "title": "Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02057", "title": "Optimizing Effective Training Time for Large-Scale Recommendation Systems", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "effective-training-time", "detail_path": "reproductions/2610.02057-effective-training-time/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02045", "title": "Form and Void: Entangled Composition through an Autonomous AI Agent", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02038", "title": "Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02021", "title": "Task-Adaptive Grounded 3D-Programmers Using 2D VLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02019", "title": "Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02012", "title": "Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02005", "title": "Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02002", "title": "Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "mem-plus-plus", "detail_path": "agent-research/2610.02002-mem-plus-plus/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01999", "title": "From Reasoning Failures to Composable Video Spatial Intelligence", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01981", "title": "Universal interpolation for deep residual self-attention networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01973", "title": "Token-Level Video Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "tvrl", "detail_path": "post-training/2610.01973-tvrl/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01962", "title": "SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01944", "title": "Anti-Persona: Disrupting Unauthorized Identity Binding and Recognition in Personalized Vision--Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01939", "title": "Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01921", "title": "Cross-Lingual Alignment for Decoder-Only Models using MoE Routers", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01917", "title": "MoLE: Mixture of Latent Experts for Complementary Visual Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01894", "title": "A foundation for systematic analysis of transformers and RNNs for tractography", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01882", "title": "Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01846", "title": "Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01835", "title": "Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01833", "title": "Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01821", "title": "Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01815", "title": "Debias Anything: Fairness with Diversity without Supervision in Diffusion Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01794", "title": "Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01785", "title": "VETO: Video Efficient Token Optimization for Vision Language Models", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "veto", "detail_path": "foundation-models/2610.01785-veto/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/veto-a100-20261002.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.01769", "title": "CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01766", "title": "VideoEvolve: Evolving Agent Harnesses for Video Temporal Grounding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01754", "title": "Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01746", "title": "End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01741", "title": "ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive Injection", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02284", "title": "Effects of interpulse-interval variation on deep-learning classification of bat vocalizations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01710", "title": "CoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01705", "title": "AgentWebRec: Compact Evidence Fusion over the Agent Web for Personalized Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "agent-web-rec", "detail_path": "reproductions/2610.01705-agent-web-rec/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01687", "title": "Architectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01670", "title": "Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01649", "title": "CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01640", "title": "Not All Error Yields to Scale: Where Scaling Stops in Vision-Language Inference", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01637", "title": "Fusing Visual and Textual Representations via Multi-layer Fusing Transformers for Vietnamese Visual Question Answering", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01625", "title": "Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01605", "title": "Hob-VL: A Benchmark for Visually Grounded Boolean Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01595", "title": "Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01578", "title": "The hidden advantage of mask resampling: a theory of masked autoencoders", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01569", "title": "Managing Context and Communication in Distributed Agentic UAV Swarms", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01564", "title": "Chaining Skills to Hijack LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01537", "title": "FedFit: Federated Fine-Tuning of LLMs via Vector-Bank Parameterization and Quantization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01533", "title": "Neither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "gris", "detail_path": "reproductions/2610.01533-gris/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01531", "title": "Towards Reliable Vision-Language Models for Autonomous Driving", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01530", "title": "Calibrating Prediction Timeliness Through Multi-Objective Hyperparameter Optimization for Remaining Useful Life Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01514", "title": "How the Audit Rule Shapes Faithful Factor Explanations in LLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01513", "title": "Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01509", "title": "Sharpening Tax in Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "sharpening-tax", "detail_path": "post-training/2610.01509-sharpening-tax/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01508", "title": "OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01506", "title": "MCRI: A Four-Dimensional Framework for Analyzing and Evaluating Agent Skills", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01499", "title": "VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01496", "title": "SALD: Self-Referenced Advantage Learning for Diffusion Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01492", "title": "Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01491", "title": "Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01490", "title": "The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01451", "title": "A Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and Guidance", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01434", "title": "MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "mwop", "detail_path": "foundation-models/2610.01434-mwop/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01415", "title": "Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "belief-state-pos", "detail_path": "agent-research/2610.01415-belief-state-pos/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01395", "title": "AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "af-muon", "detail_path": "foundation-models/2610.01395-af-muon/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01389", "title": "AiSearch: Interactive Multi-Modal Search with VLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01364", "title": "LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01349", "title": "PACE: Provenance-Aware Capability Enforcement for Tool-Using LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "pace-capability", "detail_path": "agent-research/2610.01349-pace-capability/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01345", "title": "ARCCS: An Automated Regulatory Compliance Checking System", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01325", "title": "PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01316", "title": "What Wins a Vote? Formatting, Length, and Lexical Diversity in the French Compar:IA LLM Arena", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01286", "title": "Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01270", "title": "Not All Is Lost: Repairing Lossy User Preference States of Personalization Encoders", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "repair-state", "detail_path": "reproductions/2610.01270-repair-state/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01257", "title": "Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01256", "title": "DeFA: Dependency-Guided Failure Attribution for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "defa", "detail_path": "agent-research/2610.01256-defa/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01243", "title": "When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated Prompts", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01207", "title": "Dependency-Aware Reward Shaping for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "dars", "detail_path": "post-training/2610.01207-dars/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01195", "title": "Federated Agent Optimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01192", "title": "FlashBack: Knowing When to Remember in Streaming Vision-Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01184", "title": "ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01180", "title": "Skeleton-and-Strategy Prompting: Training-Free Negation Understanding for Vision-Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01172", "title": "Learning Rate Transfer for Hybrid Transformer-SSM Architectures", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01166", "title": "CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI Assessment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02270", "title": "Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01138", "title": "Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01127", "title": "Counting and Min-Cost Encoding for Tokenization in Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02267", "title": "Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01102", "title": "MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01093", "title": "OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01073", "title": "Safety Must Survive Self-Improvement: Why Failures Persist and How Agents Recover", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "safe-self-improvement", "detail_path": "agent-research/2610.01073-safe-self-improvement/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01054", "title": "Capturing In-Context Learning Dynamics with Task Operators", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01045", "title": "Empty Commitments: When Agents Promise What They Cannot Deliver", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01042", "title": "Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01037", "title": "SLIM: Simplex-Lattice Interpolation Merging", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01027", "title": "LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01023", "title": "Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01017", "title": "Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03796", "title": "ProsaBuddy: Assisting Mechanized Real-Time Schedulability Analysis with LLM-based Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00984", "title": "HADRec: A Hierarchy-Aware Drug Recommendation Framework by Fusing Molecular Knowledge and Electronic Health Record", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00983", "title": "The Devil Is in the Reconstruction Loss Scale: Rethinking Optimization in LLM Quantization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00981", "title": "NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00979", "title": "RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00977", "title": "ABSENTIA: Detecting Broken Access Control Vulnerabilities in Web Applications", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00973", "title": "Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00972", "title": "VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "veriharness", "detail_path": "agent-research/2610.00972-veriharness/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00969", "title": "A Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00964", "title": "RPTune: Learned Context Curation for LLM Catalog Search", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "rptune", "detail_path": "reproductions/2610.00964-rptune/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00958", "title": "Role-aware Heuristic Episodic Attention for Conversational LLMs", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "rea", "detail_path": "foundation-models/2610.00958-rea/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00952", "title": "A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00922", "title": "EyeTAG: Eye Trajectory-Aware Gaze Estimation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00917", "title": "Finding the Right Fit: Model-Harness Interactions across Agent Tasks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00906", "title": "ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "active-saddler", "detail_path": "agent-research/2610.00906-active-saddler/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00905", "title": "Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00899", "title": "TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00890", "title": "Cross-Benchmark Transfer from RL on Agentic Coding Tasks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00885", "title": "FORALL-LEAN-AGENT for Auditable Reasoning in Formal Mathematics and Software Verification", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00883", "title": "DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00881", "title": "Machine Translation for Sign Languages", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00878", "title": "UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00872", "title": "MemFit: Efficient Long-Term Agentic Memory", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "memfit", "detail_path": "agent-research/2610.00872-memfit/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00870", "title": "An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00864", "title": "Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00855", "title": "Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10560", "title": "Strategic Governance of AI Models in Earth Science", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00849", "title": "Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00848", "title": "Geometric Similarity in VLM Low-Level Vision Representations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02376", "title": "Coco: An Agentic Copilot for the Hardware--Software Co-Design Lifecycle", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00838", "title": "SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "sharpo", "detail_path": "post-training/2610.00838-sharpo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00825", "title": "Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00809", "title": "Paying for Too Many Tokens? Valid and Cost-Efficient Multimodal LLM Annotation with Simple Heuristics", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00795", "title": "Can large language models unlock discrete data in ophthalmic diagnostic reports?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00779", "title": "Effective Synthetic Data Curation Requires Group-Level Signals", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00767", "title": "Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00758", "title": "Scalable Multi-Task Inverse Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03792", "title": "What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00717", "title": "Sequential Functional Structured Tucker Compression for Large Language Model Attentions", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00710", "title": "ReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00705", "title": "Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00694", "title": "How Divergence Becomes Decision Flips in Compressed Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00680", "title": "Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00677", "title": "Harnessing Vision-Language Models for Perceptual Quality Assessment and Autonomous Content Adjustment in Augmented Reality", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00675", "title": "LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00673", "title": "Closing the Loop: Practical Training Recipes for Looped Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00666", "title": "VisionQ: VLM-as-a-Judge Taxonomy, Dataset and Benchmark for Qualitative Analysis in Computer Vision", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00665", "title": "Analysis of Quantized and Efficiently Adapted Protein Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00663", "title": "Backdoor Containment via Expert Quarantine and Shutdown in LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00661", "title": "Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00654", "title": "When More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00651", "title": "Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00650", "title": "Self-Evolving Coding Rules for AI Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "rule-evolve", "detail_path": "agent-research/2610.00650-rule-evolve/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00648", "title": "Incident-Arena: Getting agents to the last nine of reliability", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00636", "title": "CompMat-Bench: Benchmarking AI Agents for Computational Materials Science", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00629", "title": "ASAD: Adaptive Software Agents for Debugging", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00623", "title": "HAWK: Rethinking Multimodal Drafting for Speculative Decoding", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "hawk", "detail_path": "foundation-models/2610.00623-hawk/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00622", "title": "Understanding and Mitigating Library-Related Issues in LLM-Generated Code", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00619", "title": "Beyond Supra-Competitive Outcomes: Collusive Behaviour in Deep Reinforcement Learning for Optimal Execution Games", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00613", "title": "Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00610", "title": "Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRA", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00609", "title": "Legal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00604", "title": "MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00592", "title": "ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00590", "title": "Towards Hierarchical Cyber Defense with Large Language Models: From Planning to Execution", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00574", "title": "Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00573", "title": "FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00568", "title": "Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00562", "title": "Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00559", "title": "PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00557", "title": "No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00541", "title": "Random Recursive Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00540", "title": "Assessing the Impact of Language Disparity on Multilingual Linguistic Ability in Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00511", "title": "Before Agents Decide: Epistemic Action in LLM-Based Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00499", "title": "Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Serving", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00497", "title": "Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00487", "title": "ScaffoldM3C: A Multimodal Sequential Monte Carlo Framework for Generative Stable Construction Planning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00465", "title": "AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00437", "title": "JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "jev-spawn", "detail_path": "agent-research/2610.00437-jev-spawn/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00435", "title": "How AI Agents Discover Scientific Equations: From Hydrotope Rediscovery to New Water-Wave Amplitudes", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00432", "title": "XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02247", "title": "Toward Controlling Biology with Language:Offline Learning of Prompt-Conditioned Interventions for Cells, Organoids, and Biobots", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00431", "title": "ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00430", "title": "Memetic Trojans: Social Contagions as Carriers of Adversarial Payloads in Agent Networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00426", "title": "IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "irekogpt", "detail_path": "foundation-models/2610.00426-irekogpt/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00425", "title": "Code That Works, Environments That Don't: Measuring Environment Reproducibility in AI-Generated Software", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00406", "title": "LLM-as-a-Judge for Low-Resource Languages: Adapting Ragas and Comparative Ranking for Romanian", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00400", "title": "Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00399", "title": "Metacognitive Reasoning in Energy Based Models using Instance Based Learning Theory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00398", "title": "WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00388", "title": "T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "t2spo", "detail_path": "post-training/2610.00388-t2spo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00385", "title": "FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06902", "title": "Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00374", "title": "Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00372", "title": "When Harnesses Lose the Signal: Causal Evaluation of Recovery in LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03780", "title": "OceanMind: A multi-agent AI system for ocean diagnosis", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00367", "title": "MoRA: MoE Pruning via Router Bias Learning and Expert Approximation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00363", "title": "Deep Learning for Anomaly Detection in Railway Systems: A Structured Survey", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00354", "title": "Proof-Gated Signing: Solver-Checked Transaction Guards that Hold Under State Drift for Onchain AI Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00333", "title": "LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "lego-opd", "detail_path": "post-training/2610.00333-lego-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00332", "title": "The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "weakest-link", "detail_path": "post-training/2610.00332-weakest-link/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02241", "title": "Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10556", "title": "LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00317", "title": "DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "drift-opd", "detail_path": "post-training/2610.00317-drift-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00316", "title": "DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00313", "title": "Rules to Tools: Executable Checks for LLM Agents in Scientific Computing", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06896", "title": "Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00302", "title": "Decoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08830", "title": "MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03759", "title": "BridgeCast: Bridging Ocean Wave Forecasts to Reanalysis via Flow Matching with Exogenous Variables", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06892", "title": "Axiom Satisfiability of Linear Rewards in Alignment", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12495", "title": "Kairos: Toward a Byte-Level Foundation Model for Every Modality", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10552", "title": "Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12494", "title": "Algebraic Integer Quantization for Machine Learning Applications", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08822", "title": "A Vehicle-Integrated Approach to Digital Twin Deployment for Bridges Through Drive-By Sensing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10550", "title": "Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10549", "title": "Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08818", "title": "Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00256", "title": "Verification Pulses and the Cost of Escaping Wrong Consensus", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00253", "title": "System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00251", "title": "The Null Is the Hard Part: Exact Tests for Memorization in Generative Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08813", "title": "Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08811", "title": "KVFetch: Temporal Prefetching for the Missing Half of KV Cache Compression", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03741", "title": "Logit-Aware MIMO AirComp for Distributed Mixture-of-Experts LLM Inference over Wireless Edge Networks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00223", "title": "A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00204", "title": "Query Independent Variable Rate Visual Token Coding", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00197", "title": "Comedic Fool's Gold: Reward Exploits and Countermeasures in Conversational Humor", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00196", "title": "GPEC: Efficient Pre-LLM Gaussian Process Embedding Correction for Cardiac Video Caption Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00188", "title": "Uncertainty-Aware RL-Controlled Adaptive 3D Mapping", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00182", "title": "Localizing Post-Wire Semantic Changes in MCP Agent Frameworks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06874", "title": "Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00106", "title": "SyntheticHLS: Building Diverse Synthetic High-Level Synthesis Datasets using LLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00097", "title": "DramaAgent: Agentic Storytelling Video Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00096", "title": "FACET at WMT 2026 Automated Translation Quality Evaluation Task", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00093", "title": "Safety in Self-Evolving Agents: A Survey", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00092", "title": "BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00084", "title": "Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00069", "title": "A Framework for Egocentric and Exocentric Procedural Understanding via Temporal Segmentation and Semantic Abstraction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00054", "title": "The First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00047", "title": "Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00040", "title": "DSSR-3D: Decoupled Reasoning for View-Dependent Referring in 3D Gaussians", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00035", "title": "Integrating Fairness and Explainability in a Multiple Instance Reinforcement Learning System", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00031", "title": "Seeing the City or Recognizing the Place? What Street-View Imagery Adds Beyond Existing Urban Data in VLM-Based Urban Sensing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00025", "title": "Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00024", "title": "Encoded but Disconnected: Decomposing Vision-Language Model Failures under a Patching Null", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12474", "title": "TTS-Q: Perception-Guided Post-Training Quantization of Text-to-Speech Diffusion Transformers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00015", "title": "From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00012", "title": "When Do Causal World Models Help Modular LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00010", "title": "Heavy-Tailed Memory Traces in Long-Horizon Language Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08793", "title": "Adaptive Workflow Intelligence: A Cognitive Architecture for Context-Driven Enterprise Automation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2510.15831", "title": "VISTA: A Test-Time Self-Improving Video Generation Agent", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08781", "title": "IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08778", "title": "Sherpa: Teaching LLMs to Teach Adaptively", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08773", "title": "AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08670", "title": "Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08561", "title": "Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08108", "title": "Enhancing Diffusion Language Models with Autoregressive Post-Training Weights", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08082", "title": "POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08077", "title": "Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07898", "title": "FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07842", "title": "Privileged Context as Drift in On-Policy Self-Distillation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07781", "title": "Quantization Effects on Tool-Failure Recovery Vary Across Prompts and Evaluation Designs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07767", "title": "TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07739", "title": "Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07731", "title": "Learning to Retrieve via Reinforcement Learning in Embedding Space", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07730", "title": "SanSi: A Looped Typed Decision Model for System 1.5 Thinking", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07654", "title": "Does On-Policy Distillation for Safety Pose Backdoor Risks?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07587", "title": "Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07545", "title": "Quality-Aware Self-Correcting Speech Translation on an Edge Device", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07518", "title": "Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07247", "title": "Learning What to Distill: Bilevel Top-K Token Selection for Self-Distillation in Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07226", "title": "Minimal Witness Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07212", "title": "Reward-Driven Learning under Prompt-Level Differential Privacy", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07177", "title": "CLM-as-a-Judge: Evaluating an Open Contrastive Decision Model on Public Judge Benchmarks", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07043", "title": "TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07023", "title": "Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06962", "title": "Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06947", "title": "FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06861", "title": "When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06851", "title": "Base Models Can Reason By Taking a Cue From Training Data", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06833", "title": "Towards Looped Models Done Right, Part II: Rethinking at Fixed Points", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06829", "title": "CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06804", "title": "Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06782", "title": "T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06744", "title": "ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06729", "title": "Improving Diversity in LLM Short Story Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06671", "title": "Learning What to Imitate: Entropy-Aware Distribution Mixing", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06648", "title": "Representation-Space MMD for Diffusion Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06637", "title": "Long-Horizon Textual World Modeling through Structured Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06439", "title": "Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06360", "title": "Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05935", "title": "ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05699", "title": "Planetary Geospatial Foundation Models for Global Public Health", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05600", "title": "An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05481", "title": "CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05446", "title": "Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05373", "title": "Towards Unbiased On-Policy Distillation for Block Diffusion Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05367", "title": "AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05329", "title": "Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05308", "title": "RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05282", "title": "Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05265", "title": "Loopy: Low-Bit Quantization Framework for Looped Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05200", "title": "Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05139", "title": "Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05125", "title": "Bayesian Entropy-based Reordering for Calibrated Diffusion Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05099", "title": "Small Agents with Semantic Search: Efficient Multilingual Code Localization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04950", "title": "How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04914", "title": "Monitorability Disposition in Large Reasoning Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04899", "title": "Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04888", "title": "No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04882", "title": "ResOPD: Tail Residualization for Sparse On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04851", "title": "CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04845", "title": "Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04604", "title": "Anticipating the Consequences of Curriculum Decisions with Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04596", "title": "DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04441", "title": "LocusRL: Diagnosing LLM Reward and Policy Interventions in Competitive Games", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04412", "title": "Large Language Models and Augmented Democracy", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04344", "title": "Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04328", "title": "Bidirectional Preference Synthesis: Learning Prompt-Conditioned Preferences from Boundary Failures", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04299", "title": "Questioning the Questions: Sustaining Self-Evolution in Reasoning Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04272", "title": "Rethinking Self-Distillation for Multi-Teacher Capability Merging", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04269", "title": "Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04261", "title": "Playing social deduction games with reinforcement fine-tuned large language models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04158", "title": "How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04132", "title": "PB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03984", "title": "Teaching Agents to Code Reliably", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03702", "title": "LESSER: Post-Training Data Selection with Output-Layer Gradients", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "lesser", "detail_path": "post-training/2610.03702-lesser/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03665", "title": "Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03515", "title": "Learning from Repaired Reasoning: Root-Cause-Guided On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03480", "title": "Metropolis-Hastings Dominates Importance Resampling for Policy Composition", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03454", "title": "Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03369", "title": "Mixture-of-Experts for Cryptocurrency Order Execution: Training Stability, Tail Risk, and Failure Modes", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03361", "title": "Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "follow-the-winners", "detail_path": "post-training/2610.03361-follow-the-winners/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03223", "title": "AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "adastep", "detail_path": "agent-research/2610.03223-adastep/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03195", "title": "Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03190", "title": "Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03185", "title": "Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03109", "title": "Emergent Structure in the Marginal Attention Space of Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03063", "title": "HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02986", "title": "OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02886", "title": "Misinformation Without Triggers: From Factual Answers to Downstream Decisions", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02856", "title": "Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02835", "title": "All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02828", "title": "FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02819", "title": "Text-Centric Post-Training for Omni-Modal Reasoning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02781", "title": "OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02766", "title": "Exact Memory-Time Optimization for Prefix-Cached Language Model Serving", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02744", "title": "EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02700", "title": "Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02695", "title": "Test-time Calibration Learning for Large Language Model Reasoning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02614", "title": "What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse Perspectives", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02554", "title": "Test-time Multi-agent Coordination by Decomposed Value Gradient Flow", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02486", "title": "From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02466", "title": "SD-DPC: Sparse Dictionary Differentiable Predictive Control", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02444", "title": "Counterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02359", "title": "Lexicographic Multi-Objective On-Policy Distillation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02324", "title": "Slow-Fast Multi-Teacher On-Policy Distillation for Capability Preservation", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02206", "title": "KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02191", "title": "The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02190", "title": "Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02189", "title": "Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02173", "title": "Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02140", "title": "Finetuning with Sampling: SFT Learns Better Than You Think", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02039", "title": "CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "carm", "detail_path": "post-training/2610.02039-carm/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02015", "title": "On Language Drift during RLVR Post-Training", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01955", "title": "Do Your Own Research: Learning to Forecast by Learning to Search", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01908", "title": "Same Reward, Different Skills: When Multimodal RL Learns to Look", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01896", "title": "Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "gmc-grpo", "detail_path": "post-training/2610.01896-gmc-grpo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01892", "title": "Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01828", "title": "The Asymptotics of Language Model Alignment with Memory", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01560", "title": "AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01548", "title": "Range-GRPO: Policy Optimization via Pairwise Relations among Reward Intervals", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "range-grpo", "detail_path": "post-training/2610.01548-range-grpo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01511", "title": "GAW-PO: Preference Optimization with Gradient-Aligned Token Weights", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "gaw-po", "detail_path": "post-training/2610.01511-gaw-po/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01278", "title": "SCOPE-AD: Sequential cost-aware ordinal-belief planning with energy-based models for diagnostic agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01275", "title": "Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01238", "title": "Mixture-Trained Merging for Unified Multi-Objective Models", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01234", "title": "ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01161", "title": "My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "my-fault", "detail_path": "post-training/2610.01161-my-fault/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01128", "title": "Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01076", "title": "GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR Events", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01066", "title": "Probe with Participation Trophies: Random-Reward RL as a Probe of LLM Capability", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01026", "title": "It Takes Workflows to Evolve Better Workflows", "review_decision": "known", "frozen_implementation_status": "existing_record", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "flowright", "detail_path": "agent-research/2610.01026-flowright/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00991", "title": "Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00988", "title": "Auditable Algebraic Counting Field for Cryptic-Pocket Detection from Apo Structures", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00954", "title": "Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00903", "title": "Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00898", "title": "When Do Biological Reasoning Models Use Their Biological Inputs?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00888", "title": "Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00852", "title": "Child-Adapted Structured Phonological Representations for Interpretable Speech Sound Analysis", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.16490", "title": "From Growing to Looping: A Unified View of Iterative Computation in LLMs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_in_this_review", "current_status": "not_catalogued", "observations": [] } ] }