TIAO: Token Importance-Aware Policy Optimization for Text Summarization¶

L1 core-mechanism diagnostic. Executes token dependency and two-scale credit, not 7B model training.

Paper information¶

Field	Details
Paper	TIAO: Token Importance-Aware Policy Optimization for Text Summarization
Organization	First-author affiliation: National University of Defense Technology
First public release	2026-09-15 (arXiv v1)
Authors' code	Public implementation
Adapter / method	`tiao`
Local reproduction code	`src/auto_research/post_training/latest_20260916_followup.py`

Original paper¶

Motivation and method¶

Estimate dependency from changes in token probabilities before and after masking the source document, then reshape trajectory advantages and concentrate updates on important tokens.

flowchart LR
  I[Public input and current state] --> M[TIAO mechanism]
  M --> A[Auditable intermediates]
  A --> O[Output or state update]

Key figure from the paper¶

Figure 1: Overall method and components. From the original paper; copyright remains with the authors.

Core computation and code mapping¶

The reference kernel preserves the decisive ranking, gating, preference direction, credit weighting, or state transitions and exposes auditable statistics. Three-seed fixtures check invariants and edge cases, not paper capability.

Paper results¶

Accuracy, speed, training loss, and benchmarks are original paper results only. Local results are not directly compared with them or extrapolated to online gains.

Local reproduction¶

See the three-seed results. The common receipt marks diagnostic_only=true, ineligible for formal capability ranking.

CUDA ran on an NVIDIA A100; see the sanitized GPU receipt. The receipt omits hostnames, SSH aliases, and driver/build strings.

Reproduction boundaries¶

Token dependency and two-scale credit are implemented locally. No 7B model was trained.