{
  "schema_version": 3,
  "track": "post-training",
  "window": {
    "start": "2026-10-12",
    "end": "2026-10-15"
  },
  "query_matrix": [
    "post-training",
    "preference-optimization",
    "llm-rl",
    "on-policy-distillation",
    "reward-model",
    "process-reward",
    "test-time-rl",
    "opd",
    "opd-abbreviation",
    "rlvr-abbreviation",
    "policy-llm-abbreviation"
  ],
  "candidate_count": 1103,
  "triage_counts": {
    "new": 749,
    "reviewed": 314,
    "implemented": 40
  },
  "requested_window": {
    "start": "2026-10-13",
    "end": "2026-10-15"
  },
  "announcement_overlap_days": 1,
  "recall_mode": "late-index",
  "announcements": {
    "enabled": true,
    "sources": [
      {
        "announced_on": "2026-10-15",
        "expected_entries": 58,
        "parsed_entries": 58,
        "sections": [
          {
            "kind": "replacement",
            "shown": 58,
            "expected": 58
          }
        ],
        "sha256": "bd0a082207a2b5753747b7f57cb83a331372ad542798546924652db047c8a38f",
        "parse_complete": true,
        "source_url": "https://arxiv.org/list/cs.CL/new?show=2000",
        "category": "cs.CL",
        "status": "retrieved",
        "coverage_complete": true,
        "publication_dates_resolved": true,
        "metadata_resolution_failures": [],
        "review_complete": false,
        "watermark_eligible": false
      },
      {
        "announced_on": "2026-10-15",
        "expected_entries": 486,
        "parsed_entries": 486,
        "sections": [
          {
            "kind": "new",
            "shown": 184,
            "expected": 184
          },
          {
            "kind": "cross-list",
            "shown": 121,
            "expected": 121
          },
          {
            "kind": "replacement",
            "shown": 181,
            "expected": 181
          }
        ],
        "sha256": "af80fbf6c132fe5fd7493131590ab8aaf0fec622c63ea528a3c851c2a8f3c347",
        "parse_complete": true,
        "source_url": "https://arxiv.org/list/cs.LG/new?show=2000",
        "category": "cs.LG",
        "status": "retrieved",
        "coverage_complete": true,
        "publication_dates_resolved": true,
        "metadata_resolution_failures": [],
        "review_complete": false,
        "watermark_eligible": false
      }
    ],
    "coverage_complete": true,
    "review_complete": false,
    "watermark_eligible": false
  },
  "candidates": [
    {
      "arxiv_id": "2610.20606",
      "published": "2026-10-14T17:59:52Z",
      "updated": "2026-10-14T17:59:52Z",
      "revision": 1,
      "metadata_sha256": "ad5df8a06e4eb06dca6f16ef23f95b1c92ae88f119165cd8098476898bd8dd30",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20607",
      "published": "2026-10-14T17:59:52Z",
      "updated": "2026-10-14T17:59:52Z",
      "revision": 1,
      "metadata_sha256": "ce008f9de57e6db57ab7d1c7aa5bf81abbe5d625fddbc65496f15f4cb9e807f7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20597",
      "published": "2026-10-14T17:59:28Z",
      "updated": "2026-10-14T17:59:28Z",
      "revision": 1,
      "metadata_sha256": "daaf74202e484916259563cf5ccb43749ad1998c8244b340c7c03b2219e2b601",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20588",
      "published": "2026-10-14T17:58:08Z",
      "updated": "2026-10-14T17:58:08Z",
      "revision": 1,
      "metadata_sha256": "7e1f3aceefdd6ee9ec1360d9d7c47d364c396294574c588a123596976dbda3cc",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20587",
      "published": "2026-10-14T17:57:57Z",
      "updated": "2026-10-14T17:57:57Z",
      "revision": 1,
      "metadata_sha256": "5ed4ccc06d3f9a4043f4440c003a07789a8000507806b84fd54578f56b294317",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20586",
      "published": "2026-10-14T17:57:40Z",
      "updated": "2026-10-14T17:57:40Z",
      "revision": 1,
      "metadata_sha256": "72716c3fbfec3c4d1fb934979ff1e6c7d1459bd6042b04dcb6776ab3f5646fc6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20585",
      "published": "2026-10-14T17:57:24Z",
      "updated": "2026-10-14T17:57:24Z",
      "revision": 1,
      "metadata_sha256": "73f21dfdb823152619f9921bc3044cfc096ec7a460bdf0d8f91c6768d301fd5a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20582",
      "published": "2026-10-14T17:57:01Z",
      "updated": "2026-10-14T17:57:01Z",
      "revision": 1,
      "metadata_sha256": "8135f87ab79b32bb2a96064a3f4cbdfb8aa4481cb2e301b71b42f7dc4e4bf649",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20576",
      "published": "2026-10-14T17:56:06Z",
      "updated": "2026-10-14T17:56:06Z",
      "revision": 1,
      "metadata_sha256": "208086140b8aca99abfab5a56ea28eac26b6dc5f9055b9449de7e3820801281f",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20572",
      "published": "2026-10-14T17:54:34Z",
      "updated": "2026-10-14T17:54:34Z",
      "revision": 1,
      "metadata_sha256": "6acad8623f1e79ee2a220f8126bbabd9b9b221fa7487106837932b0eeae52cd2",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20570",
      "published": "2026-10-14T17:53:46Z",
      "updated": "2026-10-14T17:53:46Z",
      "revision": 1,
      "metadata_sha256": "1bd7767fff30ed24b54c8262636548318eb8baaadd9c1bf0eea76bcb4fb3a6a3",
      "repository_status": "new",
      "matched_queries": [
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.20544",
      "published": "2026-10-14T17:36:33Z",
      "updated": "2026-10-14T17:36:33Z",
      "revision": 1,
      "metadata_sha256": "b316dac793e07b04ac51c00216eec2ccc0bf20a7322bfbb3d4328be5ad0dd0cf",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20538",
      "published": "2026-10-14T17:32:54Z",
      "updated": "2026-10-14T17:32:54Z",
      "revision": 1,
      "metadata_sha256": "9a12a2af5bb09b7abdc31b03f9fc16f863e42782c189535a152c567c1c67ec46",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.20534",
      "published": "2026-10-14T17:30:17Z",
      "updated": "2026-10-14T17:30:17Z",
      "revision": 1,
      "metadata_sha256": "c2db066d4188aa132e2b0e7e29fc5760f51f193dcb1600088e0f686fbb8cc1f1",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20533",
      "published": "2026-10-14T17:29:09Z",
      "updated": "2026-10-14T17:29:09Z",
      "revision": 1,
      "metadata_sha256": "e32b75b0d76a6df7eb57d175ade90f405c3894c4a5220d993082cfea9bf0c1d0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20532",
      "published": "2026-10-14T17:29:06Z",
      "updated": "2026-10-14T17:29:06Z",
      "revision": 1,
      "metadata_sha256": "1005ac6403b382784a5aa22dd2a15cf217b73f2841c1c1daba0e6f605b11fd5e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20525",
      "published": "2026-10-14T17:24:48Z",
      "updated": "2026-10-14T17:24:48Z",
      "revision": 1,
      "metadata_sha256": "0a9ff923088027fcbc9ac0dd7b621c2e19b33e56e2d088de9e32a442af212f2e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20516",
      "published": "2026-10-14T17:17:18Z",
      "updated": "2026-10-14T17:17:18Z",
      "revision": 1,
      "metadata_sha256": "6e5d4cba5fe13d9788809df22e6d401ebe30570fe3d222f8e4cdf714861a431c",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation",
        "preference-optimization",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20514",
      "published": "2026-10-14T17:16:28Z",
      "updated": "2026-10-14T17:16:28Z",
      "revision": 1,
      "metadata_sha256": "967f903c755e26c5879538e2d92bd18dc9a045561066070104b164328fa0ddad",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20512",
      "published": "2026-10-14T17:14:29Z",
      "updated": "2026-10-14T17:14:29Z",
      "revision": 1,
      "metadata_sha256": "bf9ed8e4aa2315cd1bcb9d31f8bb6f97a6bd59877d7e0f400a32e0c7c1ac2724",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20509",
      "published": "2026-10-14T17:12:56Z",
      "updated": "2026-10-14T17:12:56Z",
      "revision": 1,
      "metadata_sha256": "5c30dd99b96bccfcfa615800b7b18c174457b205518c0206ee7c76dda3b0e36b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20502",
      "published": "2026-10-14T17:08:50Z",
      "updated": "2026-10-14T17:08:50Z",
      "revision": 1,
      "metadata_sha256": "19ecf08795adb79365415ca534c30d5d2c0e2a48efec8d7d12cc17dfdc828e07",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20497",
      "published": "2026-10-14T17:06:59Z",
      "updated": "2026-10-14T17:06:59Z",
      "revision": 1,
      "metadata_sha256": "764ac63b4dc7369163c65f2ad022887b76579ea513fea636a940d1645259c93b",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20486",
      "published": "2026-10-14T16:57:47Z",
      "updated": "2026-10-14T16:57:47Z",
      "revision": 1,
      "metadata_sha256": "9ea0c1df4e2eb6b9f92b3504d89c115c83273d5d7f7ae1dbbaefa0170f80bb70",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20483",
      "published": "2026-10-14T16:55:22Z",
      "updated": "2026-10-14T16:55:22Z",
      "revision": 1,
      "metadata_sha256": "767dba9453a472d03d24082825b8441c99550dac17a3edb6712244ba8fa3837c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20479",
      "published": "2026-10-14T16:52:00Z",
      "updated": "2026-10-14T16:52:00Z",
      "revision": 1,
      "metadata_sha256": "961fc14854e0aec1917e5feb796c32ea9fecc328734a9c4d07b9427ca9a096d6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20473",
      "published": "2026-10-14T16:50:42Z",
      "updated": "2026-10-14T16:50:42Z",
      "revision": 1,
      "metadata_sha256": "73fdc4852a4ce65e1d25902602e88ae8d06992677892bf2a63076037a6f409de",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20463",
      "published": "2026-10-14T16:45:10Z",
      "updated": "2026-10-14T16:45:10Z",
      "revision": 1,
      "metadata_sha256": "0368e3a9604c86eea285c88a532fdf1cdf132dc10aacfc26ddcc334833a93cce",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20462",
      "published": "2026-10-14T16:44:29Z",
      "updated": "2026-10-14T16:44:29Z",
      "revision": 1,
      "metadata_sha256": "6da9314c507c8a94f495034bb64642a3745f24d09e7a1a8dc1e7cb6afc8c7893",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20456",
      "published": "2026-10-14T16:38:19Z",
      "updated": "2026-10-14T16:38:19Z",
      "revision": 1,
      "metadata_sha256": "4b7779dc164ae24a168e8bc3dce3ca33d5610fd7600e5f02703d0fc9512450a6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20450",
      "published": "2026-10-14T16:36:12Z",
      "updated": "2026-10-14T16:36:12Z",
      "revision": 1,
      "metadata_sha256": "bd8343994a6f2b3b88774377f246477b98bc637181536b2f78604b6c4ae85235",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20439",
      "published": "2026-10-14T16:28:22Z",
      "updated": "2026-10-14T16:28:22Z",
      "revision": 1,
      "metadata_sha256": "51c2202ed735cf5f3e1f889559d49d5739e5f6c46310a3f39affccac2a42145a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20426",
      "published": "2026-10-14T16:17:03Z",
      "updated": "2026-10-14T16:17:03Z",
      "revision": 1,
      "metadata_sha256": "a0c510c8db5cc6cace062b41ecd09b0ed4e111f79fd4450c3386557a34a28b95",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20418",
      "published": "2026-10-14T16:13:12Z",
      "updated": "2026-10-14T16:13:12Z",
      "revision": 1,
      "metadata_sha256": "bf107d17681c303e60c2bf53fd0f7f6b880f2c2dbb19ff8878ae213aabfe20e4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20416",
      "published": "2026-10-14T16:13:03Z",
      "updated": "2026-10-14T16:13:03Z",
      "revision": 1,
      "metadata_sha256": "a5a65e53721ea69f2315de91e4ea61e34d388c9ecd1f7cb8c7fa198273663c1d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20415",
      "published": "2026-10-14T16:12:56Z",
      "updated": "2026-10-14T16:12:56Z",
      "revision": 1,
      "metadata_sha256": "c3cd355ade009c8f8b213b9fc77b393681d3417ccbc0b7a3d2dae71e1ea7c97c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20413",
      "published": "2026-10-14T16:11:14Z",
      "updated": "2026-10-14T16:11:14Z",
      "revision": 1,
      "metadata_sha256": "bec5c89eb4810be609f5356ab4f5e3d3cb54b0513421a7e1b107c71447eec2ba",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20409",
      "published": "2026-10-14T16:08:28Z",
      "updated": "2026-10-14T16:08:28Z",
      "revision": 1,
      "metadata_sha256": "771281c6f36d65509a180711f915f6d0e51f216d091b6f1cdb3643cc1d8b561a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20402",
      "published": "2026-10-14T16:04:49Z",
      "updated": "2026-10-14T16:04:49Z",
      "revision": 1,
      "metadata_sha256": "17d66e369146fada45f64ab91b4b53184a2da1795973d6844652a9cd90937168",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20401",
      "published": "2026-10-14T16:03:12Z",
      "updated": "2026-10-14T16:03:12Z",
      "revision": 1,
      "metadata_sha256": "5f189dd4e678c3601a16529e34519bec0d581bc663233b227ae77847d4c64337",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.20400",
      "published": "2026-10-14T16:03:02Z",
      "updated": "2026-10-14T16:03:02Z",
      "revision": 1,
      "metadata_sha256": "493c6ed28f6e642c9077d74acf1161bec1a1e96b32fc27b3d436dd47b5b26149",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20399",
      "published": "2026-10-14T16:03:01Z",
      "updated": "2026-10-14T16:03:01Z",
      "revision": 1,
      "metadata_sha256": "abc57665d700f2a1aa6c421e892df31c8c3b47eca06148add8295ed8097c66a8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20396",
      "published": "2026-10-14T16:00:20Z",
      "updated": "2026-10-14T16:00:20Z",
      "revision": 1,
      "metadata_sha256": "6728d73a2fc3678ffc1e3530bab83aaf7b023d002698cfd8067026749c9158d5",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20392",
      "published": "2026-10-14T15:55:10Z",
      "updated": "2026-10-14T15:55:10Z",
      "revision": 1,
      "metadata_sha256": "d170d335b87f5555383cfb68d84bf245fed0d174ce31a07bef91cbef48ed86bc",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20375",
      "published": "2026-10-14T15:45:01Z",
      "updated": "2026-10-14T15:45:01Z",
      "revision": 1,
      "metadata_sha256": "0af2270804926c425d916fe3d7410c7c56baf676371a9fcfaf271833f64a24ca",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20369",
      "published": "2026-10-14T15:41:24Z",
      "updated": "2026-10-14T15:41:24Z",
      "revision": 1,
      "metadata_sha256": "be4027a2e275f4201fc7ba580e01c7e770d86d69f6b41acdf3304bcfa61261b0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20363",
      "published": "2026-10-14T15:37:48Z",
      "updated": "2026-10-14T15:37:48Z",
      "revision": 1,
      "metadata_sha256": "3b67c8799bc875ee1a36f353bb848dd4a52fb3830183821c347d322c1fcbd85b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20353",
      "published": "2026-10-14T15:29:40Z",
      "updated": "2026-10-14T15:29:40Z",
      "revision": 1,
      "metadata_sha256": "d429c8f0e237e7d03400178298fdef64267d37b3bd2dca097ba5f87013d92752",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20350",
      "published": "2026-10-14T15:27:50Z",
      "updated": "2026-10-14T15:27:50Z",
      "revision": 1,
      "metadata_sha256": "7d0b2b73c3ab34777297c16d42bb668caf28b963c92c2b543f56949859ff8b8a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20349",
      "published": "2026-10-14T15:27:34Z",
      "updated": "2026-10-14T15:27:34Z",
      "revision": 1,
      "metadata_sha256": "e52050d3b0558066fa880ae6c706c53c5ebcb64873b2b21ee0f35e65b8fdea24",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20347",
      "published": "2026-10-14T15:26:23Z",
      "updated": "2026-10-14T15:26:23Z",
      "revision": 1,
      "metadata_sha256": "797a0122e3665ad44303d98629a29d8243687421543dd221107aa8b5fc18fd93",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20342",
      "published": "2026-10-14T15:22:43Z",
      "updated": "2026-10-14T15:22:43Z",
      "revision": 1,
      "metadata_sha256": "0033a96c93e6bdc51e73baec3e1e53e61e6b0a5cc21ad12114e2a611373807d4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20337",
      "published": "2026-10-14T15:19:08Z",
      "updated": "2026-10-14T15:19:08Z",
      "revision": 1,
      "metadata_sha256": "f16f04aa2468697af339a0f3effdf3a9313ed5a83b7671d3f44e025becbc44fe",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20334",
      "published": "2026-10-14T15:16:50Z",
      "updated": "2026-10-14T15:16:50Z",
      "revision": 1,
      "metadata_sha256": "a406192e99f95a01775ccce5870e6e40a41539702e48989290d5ff21e9e4e4de",
      "repository_status": "new",
      "matched_queries": [
        "process-reward",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20331",
      "published": "2026-10-14T15:14:43Z",
      "updated": "2026-10-14T15:14:43Z",
      "revision": 1,
      "metadata_sha256": "43e8e7dab5061e278243fd2ef77a83fc06f518f3a4c92d1079bab3aae1041bfd",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20326",
      "published": "2026-10-14T15:11:29Z",
      "updated": "2026-10-14T15:11:29Z",
      "revision": 1,
      "metadata_sha256": "03208e4b545938065f18347fa71abd0b1a688754c2d86190ff6209bc9265ce63",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20318",
      "published": "2026-10-14T15:05:24Z",
      "updated": "2026-10-14T15:05:24Z",
      "revision": 1,
      "metadata_sha256": "85d3177a7ba891fb7b4bd3a5c3a493732a6ca8d281c6fe49defd772265b8853b",
      "repository_status": "new",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.20305",
      "published": "2026-10-14T14:54:20Z",
      "updated": "2026-10-14T14:54:20Z",
      "revision": 1,
      "metadata_sha256": "17568205adccafd93f82ce29252dfd0d4ca78d930ef21bc8dc35b12927f9c62d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20303",
      "published": "2026-10-14T14:54:16Z",
      "updated": "2026-10-14T14:54:16Z",
      "revision": 1,
      "metadata_sha256": "09ad0199d9208e3a8b9df801207a4c2062c8c131f11b0cc0e00e1d02c191f99c",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.20294",
      "published": "2026-10-14T14:47:50Z",
      "updated": "2026-10-14T14:47:50Z",
      "revision": 1,
      "metadata_sha256": "ab1c2c90c66c6e535c17c0517e0c5e953df08910bf9e985caa44b5985e7c4dc8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20293",
      "published": "2026-10-14T14:47:46Z",
      "updated": "2026-10-14T14:47:46Z",
      "revision": 1,
      "metadata_sha256": "f8325f572d0c5d0561946243bf10a0620c04ad3609ed1f9265d9f200239f6315",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.20288",
      "published": "2026-10-14T14:42:12Z",
      "updated": "2026-10-14T14:42:12Z",
      "revision": 1,
      "metadata_sha256": "648a00bd71df661ecfb1eb1123bc624d3a0ce8618bfadf28af38af12af630acd",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20286",
      "published": "2026-10-14T14:41:22Z",
      "updated": "2026-10-14T14:41:22Z",
      "revision": 1,
      "metadata_sha256": "ba63a8c69c4f3e7134070bcde6d3bd45f7f2d89c114670d355445844e3362368",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20277",
      "published": "2026-10-14T14:37:51Z",
      "updated": "2026-10-14T14:37:51Z",
      "revision": 1,
      "metadata_sha256": "af137693eff814a6b83da67614ec6cf907169e24b4b8681d48b28bae5a5ad01e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20274",
      "published": "2026-10-14T14:35:28Z",
      "updated": "2026-10-14T14:35:28Z",
      "revision": 1,
      "metadata_sha256": "b011893d2f48b3023e50a56c0134f634e412c6505ab40043d1b2af2cad191160",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20269",
      "published": "2026-10-14T14:31:10Z",
      "updated": "2026-10-14T14:31:10Z",
      "revision": 1,
      "metadata_sha256": "d9173622f75c195fab79c3279d5dc30d28b612315d7ea28b272d917d22a62f2f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20264",
      "published": "2026-10-14T14:29:48Z",
      "updated": "2026-10-14T14:29:48Z",
      "revision": 1,
      "metadata_sha256": "04f437a4b1eca19b547b6f130b8ff6e505bca34a605f762f8d90d3ad3edc276d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20261",
      "published": "2026-10-14T14:28:02Z",
      "updated": "2026-10-14T14:28:02Z",
      "revision": 1,
      "metadata_sha256": "5794ca8fa82dd364f5ef3f4a8134c9cc232e021ceb0492d87624533f1eaac492",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20256",
      "published": "2026-10-14T14:25:54Z",
      "updated": "2026-10-14T14:25:54Z",
      "revision": 1,
      "metadata_sha256": "bc50bee9ff1fcc27fbcaa086f407d9fee4a8553cc46446436644e99a3498cc86",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20253",
      "published": "2026-10-14T14:24:38Z",
      "updated": "2026-10-14T14:24:38Z",
      "revision": 1,
      "metadata_sha256": "31ed1e312d85bb75b54e9258e5443074a8780422ce91d5df1d3ac102d46bb9bb",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.20252",
      "published": "2026-10-14T14:23:47Z",
      "updated": "2026-10-14T14:23:47Z",
      "revision": 1,
      "metadata_sha256": "848daf465e02097b6852c18c89e3a0afcb40add1486ba03367bf01faf743c4f2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20251",
      "published": "2026-10-14T14:23:02Z",
      "updated": "2026-10-14T14:23:02Z",
      "revision": 1,
      "metadata_sha256": "e15076903b00d3a9813fc9e2240311043b787ef03cc2f0cfbe038b62a4aa0366",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20247",
      "published": "2026-10-14T14:20:19Z",
      "updated": "2026-10-14T14:20:19Z",
      "revision": 1,
      "metadata_sha256": "a9a9235a5f81a17f684541c4d8c8ab6067db22f82b17f6b9d4cc6a9eb8ef5bdf",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20243",
      "published": "2026-10-14T14:18:55Z",
      "updated": "2026-10-14T14:18:55Z",
      "revision": 1,
      "metadata_sha256": "142bbf6acba1617cfa6d8449a6b277cf44ef7b4df8649551627ac000e62dcc9a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20238",
      "published": "2026-10-14T14:16:40Z",
      "updated": "2026-10-14T14:16:40Z",
      "revision": 1,
      "metadata_sha256": "1b233d8f5476d0552b5397f04c052951f483201a3ab80b73b3c2863a4fbd9c43",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20229",
      "published": "2026-10-14T14:11:54Z",
      "updated": "2026-10-14T14:11:54Z",
      "revision": 1,
      "metadata_sha256": "3b31c85c67e6947977637879e638d3f0de9a6841c7900b36dcc6f38ab4131e58",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20218",
      "published": "2026-10-14T13:57:32Z",
      "updated": "2026-10-14T13:57:32Z",
      "revision": 1,
      "metadata_sha256": "51fe5d8f0baf9111aabc678276c6814e61d3e30188d1ab30e754924d6ed7eb01",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20217",
      "published": "2026-10-14T13:57:23Z",
      "updated": "2026-10-14T13:57:23Z",
      "revision": 1,
      "metadata_sha256": "5fa967ec0622bc2f174c9fff1bc1fd0a43f000a042bcd724dea47a7a17e96b44",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20209",
      "published": "2026-10-14T13:52:15Z",
      "updated": "2026-10-14T13:52:15Z",
      "revision": 1,
      "metadata_sha256": "39fa662c16edfe69bcb774d9f738db39bd17dc76ad99eb7240841605c0f59a05",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20203",
      "published": "2026-10-14T13:47:41Z",
      "updated": "2026-10-14T13:47:41Z",
      "revision": 1,
      "metadata_sha256": "6045a36e5ec832f3946dfee92f520f4eb4fe83cce0c84e7dcf049c548051f1aa",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20195",
      "published": "2026-10-14T13:44:30Z",
      "updated": "2026-10-14T13:44:30Z",
      "revision": 1,
      "metadata_sha256": "a0f8f77a0c1b372f59c58f81a4e367f89a9e6781ba160fceec09709b40e63550",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20187",
      "published": "2026-10-14T13:37:52Z",
      "updated": "2026-10-14T13:37:52Z",
      "revision": 1,
      "metadata_sha256": "c20685589d61d610f8a2a114fdbd3449bd2224155f32649567a732ea6bffcb04",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20179",
      "published": "2026-10-14T13:24:26Z",
      "updated": "2026-10-14T13:24:26Z",
      "revision": 1,
      "metadata_sha256": "09b1f9acd83e1e4e00b4ecfc38a4da8572f172a117e70b225edab253aa93ecda",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20174",
      "published": "2026-10-14T13:20:55Z",
      "updated": "2026-10-14T13:20:55Z",
      "revision": 1,
      "metadata_sha256": "cc31cfc5b1fc144510d8e0373a9fcdc40f805b4635fcfcefc760df1ea3f09fe2",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "preference-optimization",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20170",
      "published": "2026-10-14T13:19:59Z",
      "updated": "2026-10-14T13:19:59Z",
      "revision": 1,
      "metadata_sha256": "469ebaadb05239c10aa0bf7ca0636f02da7683ce3db7e8de613e093f224446c2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20162",
      "published": "2026-10-14T13:16:03Z",
      "updated": "2026-10-14T13:16:03Z",
      "revision": 1,
      "metadata_sha256": "338bc01f51b4ad5bfa16a381456d9d0cbc1717d70d8ef0bafd06799976f3feda",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20155",
      "published": "2026-10-14T13:12:51Z",
      "updated": "2026-10-14T13:12:51Z",
      "revision": 1,
      "metadata_sha256": "490c568be48366713f3cae08de0d3277f236fb00a8667f1c7a49ae2c4f9d24ad",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.20138",
      "published": "2026-10-14T12:55:43Z",
      "updated": "2026-10-14T12:55:43Z",
      "revision": 1,
      "metadata_sha256": "2da6ff663fcd2dd5f07a46cd065951890f2c8c8a5f37b19135c4eec5ab680258",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20136",
      "published": "2026-10-14T12:55:12Z",
      "updated": "2026-10-14T12:55:12Z",
      "revision": 1,
      "metadata_sha256": "9d945f717f36b963df7b4fbc3e75312954398f612a82147134b766a271813039",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20120",
      "published": "2026-10-14T12:44:41Z",
      "updated": "2026-10-14T12:44:41Z",
      "revision": 1,
      "metadata_sha256": "c2b40e494fbe84e30a60b9d5f585d5c70dcd90835955a1fefbcfd83d61c7bfac",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20117",
      "published": "2026-10-14T12:43:48Z",
      "updated": "2026-10-14T12:43:48Z",
      "revision": 1,
      "metadata_sha256": "0a3d282800e15df163108c5a05347374eab4b0a6d43ff3b2b5db1e9727c6ab80",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20112",
      "published": "2026-10-14T12:42:35Z",
      "updated": "2026-10-14T12:42:35Z",
      "revision": 1,
      "metadata_sha256": "282d07fac83531303b19f76a5869d868636169b558dae4a3ca829da75130b9f7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20108",
      "published": "2026-10-14T12:39:58Z",
      "updated": "2026-10-14T12:39:58Z",
      "revision": 1,
      "metadata_sha256": "10a619fadfeaf2fcfb82a2962bb6615455673f6338ced49286ad3673ae698eca",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20104",
      "published": "2026-10-14T12:38:49Z",
      "updated": "2026-10-14T12:38:49Z",
      "revision": 1,
      "metadata_sha256": "1cd5c6407011ba0198b4aa6be31ba8a6b529f258f7b40e800891dccffb85ec2f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20075",
      "published": "2026-10-14T12:13:14Z",
      "updated": "2026-10-14T12:13:14Z",
      "revision": 1,
      "metadata_sha256": "dad905b43b94a98a9fe594b62d98e899f639fdb65d1191524f8e3c271233c8d2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20071",
      "published": "2026-10-14T12:11:28Z",
      "updated": "2026-10-14T12:11:28Z",
      "revision": 1,
      "metadata_sha256": "de1056ebb966343774e8bc2a9d6ff387798a747ef0bd367a5c6a5507c4509f1e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20069",
      "published": "2026-10-14T12:07:52Z",
      "updated": "2026-10-14T12:07:52Z",
      "revision": 1,
      "metadata_sha256": "846d728075473bd29293b5802586a1c52027969b8267cf35f50e729d6a7ea9ba",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20053",
      "published": "2026-10-14T11:54:52Z",
      "updated": "2026-10-14T11:54:52Z",
      "revision": 1,
      "metadata_sha256": "c1175936560b3d2bf154df9974af18673adfe5305147d402de06646930b3495a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20041",
      "published": "2026-10-14T11:48:19Z",
      "updated": "2026-10-14T11:48:19Z",
      "revision": 1,
      "metadata_sha256": "d9fef7926cd2a2ccf1c94d68ee32b93ecd72210b8d7fdfc0c4e5eac0f950dd3c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20035",
      "published": "2026-10-14T11:43:27Z",
      "updated": "2026-10-14T11:43:27Z",
      "revision": 1,
      "metadata_sha256": "c79fec5eec31d236fd2d0e8e9fdfea621620d622c9750ec2df0a3a36c0f1e931",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20014",
      "published": "2026-10-14T11:26:19Z",
      "updated": "2026-10-14T11:26:19Z",
      "revision": 1,
      "metadata_sha256": "93f50f30ba7279a2f2b97b215e0c4af2e8095e77347c4340ef39f32e92578dca",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20012",
      "published": "2026-10-14T11:24:56Z",
      "updated": "2026-10-14T11:24:56Z",
      "revision": 1,
      "metadata_sha256": "c61a68c95c2781d29164b13fe7ca41ba22d24580e5d3d97c1c2e4b51c8d39c19",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20009",
      "published": "2026-10-14T11:23:28Z",
      "updated": "2026-10-14T11:23:28Z",
      "revision": 1,
      "metadata_sha256": "10a0d58a5a2e8d3010e8f74383200a0756f3eb2e9d08a4495d77a43e6e7f4aa2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20007",
      "published": "2026-10-14T11:22:54Z",
      "updated": "2026-10-14T11:22:54Z",
      "revision": 1,
      "metadata_sha256": "68ae40fc09d825f54ed45f308befac886ff0c8bbfcbf2acaf8e11b0999bb7596",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.20004",
      "published": "2026-10-14T11:21:30Z",
      "updated": "2026-10-14T11:21:30Z",
      "revision": 1,
      "metadata_sha256": "9fc9abb38762bcfeaeb955651be094d2ad0568ca791e117c943af96ada653cb4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19997",
      "published": "2026-10-14T11:12:56Z",
      "updated": "2026-10-14T11:12:56Z",
      "revision": 1,
      "metadata_sha256": "a3af1ee0ae71c6389e5f86e3a75ae9d3e2bb3e41a0dd46494cbdd95a6eafb2e5",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19975",
      "published": "2026-10-14T10:57:55Z",
      "updated": "2026-10-14T10:57:55Z",
      "revision": 1,
      "metadata_sha256": "629c6c7abded0da53825493890987dbaba16dd44e22812214e93562d582583f0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19968",
      "published": "2026-10-14T10:50:59Z",
      "updated": "2026-10-14T10:50:59Z",
      "revision": 1,
      "metadata_sha256": "b7a7d7e5a622a988cddb5f6cb3fc0fb354eef3c2fab879b963700a7169c1d646",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19966",
      "published": "2026-10-14T10:50:40Z",
      "updated": "2026-10-14T10:50:40Z",
      "revision": 1,
      "metadata_sha256": "0751a5d249cdbfbaf751fbb334079ac5eb6070ede9abc80329de81c53b459111",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19951",
      "published": "2026-10-14T10:33:30Z",
      "updated": "2026-10-14T10:33:30Z",
      "revision": 1,
      "metadata_sha256": "8940b6e97b8ca4ae13747eb2c3397adedea3a61594865665809ab1ebb502f671",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19946",
      "published": "2026-10-14T10:29:14Z",
      "updated": "2026-10-14T10:29:14Z",
      "revision": 1,
      "metadata_sha256": "32c691f757d31633b7c7ac97a0f9e83df83fe7c49bc988b7b8271de217496537",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19942",
      "published": "2026-10-14T10:26:08Z",
      "updated": "2026-10-14T10:26:08Z",
      "revision": 1,
      "metadata_sha256": "29bb5cb37bb77ae93183c15ec81d6a9091c4cb81e4bbc315ba1f43685ec39f2f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19931",
      "published": "2026-10-14T10:17:47Z",
      "updated": "2026-10-14T10:17:47Z",
      "revision": 1,
      "metadata_sha256": "6958bf8373eea3ca554beeee912c09b8c6e2cc32917aad1cc93b385a6c33682b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19928",
      "published": "2026-10-14T10:16:13Z",
      "updated": "2026-10-14T10:16:13Z",
      "revision": 1,
      "metadata_sha256": "c30e642cd2baa7844705f87cde58168832e0814477044619b5155b70c47234e4",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19925",
      "published": "2026-10-14T10:15:09Z",
      "updated": "2026-10-14T10:15:09Z",
      "revision": 1,
      "metadata_sha256": "c530f7366332d5cbb96676a77c9db32978497da4a86d2fe6bdc88dccd7388eb7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19920",
      "published": "2026-10-14T10:11:10Z",
      "updated": "2026-10-14T10:11:10Z",
      "revision": 1,
      "metadata_sha256": "61c23cca43eb84e5bf014023d3fd843f5150cb8273527320eec3ae8d5814c35a",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.19919",
      "published": "2026-10-14T10:09:43Z",
      "updated": "2026-10-14T10:09:43Z",
      "revision": 1,
      "metadata_sha256": "a78c9ff5e74d62565e8d5ebaaa0ebb7acc639094ff8d917316b1739ff36774c3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19915",
      "published": "2026-10-14T10:05:43Z",
      "updated": "2026-10-14T10:05:43Z",
      "revision": 1,
      "metadata_sha256": "d8d1ebe2828c833f88da8693e0be9f99016518e0f04414a7b1b466327be068ff",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19911",
      "published": "2026-10-14T10:04:24Z",
      "updated": "2026-10-14T10:04:24Z",
      "revision": 1,
      "metadata_sha256": "8afbb2d61744003ef6e763e74bcc7c9efb498c0fe513a198934773034200e92b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19910",
      "published": "2026-10-14T10:03:53Z",
      "updated": "2026-10-14T10:03:53Z",
      "revision": 1,
      "metadata_sha256": "c25c5ff4b255ed905e92b6c331f4192f3c289193738129ee5917b502878bb6b8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19901",
      "published": "2026-10-14T09:59:17Z",
      "updated": "2026-10-14T09:59:17Z",
      "revision": 1,
      "metadata_sha256": "ff33f8acd755d286bce4dabe020e32b47e548b51d84ff7b99aff8e0a77c1dd7a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19899",
      "published": "2026-10-14T09:58:02Z",
      "updated": "2026-10-14T09:58:02Z",
      "revision": 1,
      "metadata_sha256": "28e954b8d07dd61b588b8a36888886bb583a9b84defe9da54b3a052989d46378",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19893",
      "published": "2026-10-14T09:51:03Z",
      "updated": "2026-10-14T09:51:03Z",
      "revision": 1,
      "metadata_sha256": "8a5c032e39248284dd32628435e75b06fdc24e97379eb3a771f3bac17ea393ec",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19892",
      "published": "2026-10-14T09:50:59Z",
      "updated": "2026-10-14T09:50:59Z",
      "revision": 1,
      "metadata_sha256": "a6cf8b0613f3052161faf087b22c281b056b0d351f8a5823ad30472912f22cc4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19883",
      "published": "2026-10-14T09:37:20Z",
      "updated": "2026-10-14T09:37:20Z",
      "revision": 1,
      "metadata_sha256": "077f4a5354a1de683c1f1d8e5d9af6d36ad7d81cf4c4f1f58690b8ac5faa9e08",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19878",
      "published": "2026-10-14T09:32:34Z",
      "updated": "2026-10-14T09:32:34Z",
      "revision": 1,
      "metadata_sha256": "cc59432cc5cc6667c5b2f8974d031447572ab26f5f15c9f7ccadbc4faceedd4c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19876",
      "published": "2026-10-14T09:32:01Z",
      "updated": "2026-10-14T09:32:01Z",
      "revision": 1,
      "metadata_sha256": "40e4b915d523beeb483538ba763e5d7fdf40cda64d0d245f93aa0d300aa1059c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19868",
      "published": "2026-10-14T09:29:31Z",
      "updated": "2026-10-14T09:29:31Z",
      "revision": 1,
      "metadata_sha256": "4513fc8747cf2d301a71f101711c33ed386215413224ab6b053b24e12422a19d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19861",
      "published": "2026-10-14T09:24:51Z",
      "updated": "2026-10-14T09:24:51Z",
      "revision": 1,
      "metadata_sha256": "680656a18da3e6f29cd100ff2acd0db35433aa53ce30facebb2b9780ec3da7e3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19860",
      "published": "2026-10-14T09:24:05Z",
      "updated": "2026-10-14T09:24:05Z",
      "revision": 1,
      "metadata_sha256": "14a1da1ba52fecfdbc2c968987f03b205d198e7a412ce72c51b5fb1bb04e8fb5",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19855",
      "published": "2026-10-14T09:21:13Z",
      "updated": "2026-10-14T09:21:13Z",
      "revision": 1,
      "metadata_sha256": "7cd3302d41ea105d9464b7e32780cdeb8cca207c039817d8f60f27b013c96487",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19844",
      "published": "2026-10-14T09:12:57Z",
      "updated": "2026-10-14T09:12:57Z",
      "revision": 1,
      "metadata_sha256": "7a5ba60333760b25e4bd7e8f0f682869cccd87431ca9a8975d336de9eae21dbb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19832",
      "published": "2026-10-14T09:06:00Z",
      "updated": "2026-10-14T09:06:00Z",
      "revision": 1,
      "metadata_sha256": "c69a1bcfcb786829fcabddcf85c9a397b0e10bf6980f73ea50ff9b4e7033d235",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19831",
      "published": "2026-10-14T09:05:13Z",
      "updated": "2026-10-14T09:05:13Z",
      "revision": 1,
      "metadata_sha256": "8b36d19494db2d788921ba624a61be64e2195b82b8b827bb0fe31b6da8ebf72f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19827",
      "published": "2026-10-14T09:02:05Z",
      "updated": "2026-10-14T09:02:05Z",
      "revision": 1,
      "metadata_sha256": "c335839599b5b9360ff394ae15879b0b003a11fcbb06ca08f102e2a7811ac9c3",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.19822",
      "published": "2026-10-14T08:59:35Z",
      "updated": "2026-10-14T08:59:35Z",
      "revision": 1,
      "metadata_sha256": "a14b378ad41c50cd099abc40635f0c865e9e0175efbbe3cd6684b054c32c6435",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19814",
      "published": "2026-10-14T08:57:10Z",
      "updated": "2026-10-14T08:57:10Z",
      "revision": 1,
      "metadata_sha256": "cdc4aad2601a8a9e907c1826faea7bfd8a71a3b79ea1bd4d5a65ffaebbf34d9d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19813",
      "published": "2026-10-14T08:56:44Z",
      "updated": "2026-10-14T08:56:44Z",
      "revision": 1,
      "metadata_sha256": "f9a139ad5ed1e23502c262e93b038a401df4c1b4153409c6bcec9abaf3e9a162",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19811",
      "published": "2026-10-14T08:54:01Z",
      "updated": "2026-10-14T08:54:01Z",
      "revision": 1,
      "metadata_sha256": "0ec169bcb0d8614fad3502f8135769839074adfc1fac223a043ab8e5d6f6bf57",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19810",
      "published": "2026-10-14T08:50:11Z",
      "updated": "2026-10-14T08:50:11Z",
      "revision": 1,
      "metadata_sha256": "bd5e9d6faf0e60171ed0026d0fa76b7ea1feae7b2937077a2f13a15f151c4c4d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19804",
      "published": "2026-10-14T08:48:52Z",
      "updated": "2026-10-14T08:48:52Z",
      "revision": 1,
      "metadata_sha256": "17cbe4a0e2362fb65ef7ed70f95c8efec5eb8a57efcd8b06c10e3e9459f894ca",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19802",
      "published": "2026-10-14T08:45:27Z",
      "updated": "2026-10-14T08:45:27Z",
      "revision": 1,
      "metadata_sha256": "5678b8b9d03989455b4d5e22b9ac0d9e83260671cf21bedd8c74f3c2e189806a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19796",
      "published": "2026-10-14T08:40:06Z",
      "updated": "2026-10-14T08:40:06Z",
      "revision": 1,
      "metadata_sha256": "4bfa168f9b397254e736a284c39f43a584602ec14133f57a0a843a161b00f353",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19795",
      "published": "2026-10-14T08:39:41Z",
      "updated": "2026-10-14T08:39:41Z",
      "revision": 1,
      "metadata_sha256": "f88781a84f263919b4a577e737605bd105b53c8acfac12b097ccbaaf68a9c861",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19789",
      "published": "2026-10-14T08:36:31Z",
      "updated": "2026-10-14T08:36:31Z",
      "revision": 1,
      "metadata_sha256": "522e17385bd2acdfa6654fc1995d8fd681b4dd9d946d643493b4179cab43a98a",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19783",
      "published": "2026-10-14T08:31:55Z",
      "updated": "2026-10-14T08:31:55Z",
      "revision": 1,
      "metadata_sha256": "0a37ba221c406d6d91ea5d704b02df30be2fb340497f48a20beb17b40d84c3c6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19782",
      "published": "2026-10-14T08:31:07Z",
      "updated": "2026-10-14T08:31:07Z",
      "revision": 1,
      "metadata_sha256": "a0073e2d20655ac02af85928c664846a3bcc4b1cfaf44312f712d4bab8d973a2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19781",
      "published": "2026-10-14T08:30:23Z",
      "updated": "2026-10-14T08:30:23Z",
      "revision": 1,
      "metadata_sha256": "dc0bf68a18bc4bcb7a5bdd4c4ab6c1bc11e283b1c472349fd6f1e3a1e7cea67c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19773",
      "published": "2026-10-14T08:23:35Z",
      "updated": "2026-10-14T08:23:35Z",
      "revision": 1,
      "metadata_sha256": "f46b95791c2f7ed6eb6e470dc311d1678ee43d8cb4722a72f20c1f39c55f72b5",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19769",
      "published": "2026-10-14T08:19:54Z",
      "updated": "2026-10-14T08:19:54Z",
      "revision": 1,
      "metadata_sha256": "46bd00eedda95846ca7b625b147d306ef3f52f88df3fe2ecb2b5e88d92add285",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19768",
      "published": "2026-10-14T08:19:05Z",
      "updated": "2026-10-14T08:19:05Z",
      "revision": 1,
      "metadata_sha256": "59e696c76ad90fa3463ad74f635e23141a654b5b60f17ee14b3499b56f4132fd",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19767",
      "published": "2026-10-14T08:18:02Z",
      "updated": "2026-10-14T08:18:02Z",
      "revision": 1,
      "metadata_sha256": "b1c781761b8c3e853a3f68ce4b24186dbdd4fe26d2419bbc834ca2b666ed4877",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19766",
      "published": "2026-10-14T08:17:58Z",
      "updated": "2026-10-14T08:17:58Z",
      "revision": 1,
      "metadata_sha256": "38c0f3eff69375c5d607840474608ae44ce3a744f84a64866beb1b6512227828",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19761",
      "published": "2026-10-14T08:15:43Z",
      "updated": "2026-10-14T08:15:43Z",
      "revision": 1,
      "metadata_sha256": "bdc74923ff417e86520ff83a3c9edc1fdb16ee35b1935407a57947cc10cd6c5a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19758",
      "published": "2026-10-14T08:12:10Z",
      "updated": "2026-10-14T08:12:10Z",
      "revision": 1,
      "metadata_sha256": "9160951ab59a2bdbf8ca56655f2d41785fed4ec58aab7f4fa83ec44fedecc5b0",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation",
        "opd",
        "policy-llm-abbreviation",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.19743",
      "published": "2026-10-14T08:04:30Z",
      "updated": "2026-10-14T08:04:30Z",
      "revision": 1,
      "metadata_sha256": "501748ec04f806cc292e4afa94f664f8aefca236e1ead58d2a43026f8ef1eb56",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19738",
      "published": "2026-10-14T07:59:49Z",
      "updated": "2026-10-14T07:59:49Z",
      "revision": 1,
      "metadata_sha256": "4339cee738df7f08b2676432947ba83818517cc8a3f8e77136cd397085a12cf3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19731",
      "published": "2026-10-14T07:52:24Z",
      "updated": "2026-10-14T07:52:24Z",
      "revision": 1,
      "metadata_sha256": "bf8514f09e9f3cf1e4ef27848bab68705a3eee2171faa7ade8675ff71ecdc285",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19725",
      "published": "2026-10-14T07:48:38Z",
      "updated": "2026-10-14T07:48:38Z",
      "revision": 1,
      "metadata_sha256": "4a2661c296e5fa9f2d81ba08d693dd5289442c3d0099122fa18604d44c5eb58d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19721",
      "published": "2026-10-14T07:47:31Z",
      "updated": "2026-10-14T07:47:31Z",
      "revision": 1,
      "metadata_sha256": "f3f7fc5f08bd14a7413cb0e5585d33a103e26ca1e97d2d935a95806e4fa9e172",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19719",
      "published": "2026-10-14T07:44:35Z",
      "updated": "2026-10-14T07:44:35Z",
      "revision": 1,
      "metadata_sha256": "642c0bdcd79066cfb7bef42c16121878af49345dcca99244b8f636cb08722679",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19712",
      "published": "2026-10-14T07:38:54Z",
      "updated": "2026-10-14T07:38:54Z",
      "revision": 1,
      "metadata_sha256": "d51eb60a471a46a430a9176bc6da6ad83727b7e84b60e8ce57ff7785345e91a0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19705",
      "published": "2026-10-14T07:33:05Z",
      "updated": "2026-10-14T07:33:05Z",
      "revision": 1,
      "metadata_sha256": "e7a94b5094e932b867ecdccc3349afc616f5229003e6887a3207ddbd91241898",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19700",
      "published": "2026-10-14T07:23:50Z",
      "updated": "2026-10-14T07:23:50Z",
      "revision": 1,
      "metadata_sha256": "297f0bfa6a0572844d594f41cc5c4148303ee5bb2218ca7e3d437834ae11e19e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19692",
      "published": "2026-10-14T07:13:12Z",
      "updated": "2026-10-14T07:13:12Z",
      "revision": 1,
      "metadata_sha256": "f65065f3e061989eba4528092da9aa668ba6a7ce3035ce3403092735f64427a0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19687",
      "published": "2026-10-14T07:10:49Z",
      "updated": "2026-10-14T07:10:49Z",
      "revision": 1,
      "metadata_sha256": "681d8c99d1b9a642988ef025cbc01885f7a5ae1d73ca97f224ed366635e2e09f",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19685",
      "published": "2026-10-14T07:09:26Z",
      "updated": "2026-10-14T07:09:26Z",
      "revision": 1,
      "metadata_sha256": "e933c5d94e55e75ce6a4ac485b8376a2570025b71a94d8829ed585156e981747",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19683",
      "published": "2026-10-14T07:08:02Z",
      "updated": "2026-10-14T07:08:02Z",
      "revision": 1,
      "metadata_sha256": "df833a567f9718ad6e004d9f851e6c1373c1d36af9598cdb238463fcf7eaf121",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19679",
      "published": "2026-10-14T07:00:02Z",
      "updated": "2026-10-14T07:00:02Z",
      "revision": 1,
      "metadata_sha256": "cda92f7be3a3e80bd9d6180d033c4ffce047ef55d2a2b361051e986eb87507de",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19654",
      "published": "2026-10-14T06:24:39Z",
      "updated": "2026-10-14T06:24:39Z",
      "revision": 1,
      "metadata_sha256": "76a1f432147f23fdc88882cb639fc51b4b96ecb3234916cb4555d54686636519",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19652",
      "published": "2026-10-14T06:20:12Z",
      "updated": "2026-10-14T06:20:12Z",
      "revision": 1,
      "metadata_sha256": "3df318e9de604cc5b84966253a1d7739daaea95350ae41fc54aabb5e36c274b6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19642",
      "published": "2026-10-14T06:11:08Z",
      "updated": "2026-10-14T06:11:08Z",
      "revision": 1,
      "metadata_sha256": "e05c9c7b747a3a9365964da49b4beaf9919a35ad17e6324409076d4a3bec0814",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19640",
      "published": "2026-10-14T06:10:29Z",
      "updated": "2026-10-14T06:10:29Z",
      "revision": 1,
      "metadata_sha256": "3011010777ccb0e6f33fc615e39f465f50cfa0ae70bfeacedebc26516aa7335c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19636",
      "published": "2026-10-14T06:05:04Z",
      "updated": "2026-10-14T06:05:04Z",
      "revision": 1,
      "metadata_sha256": "e1f63836b0894f5b8e87933f23e8ebbdb6305c474580b2cf2515817136d226c9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19630",
      "published": "2026-10-14T06:00:29Z",
      "updated": "2026-10-14T06:00:29Z",
      "revision": 1,
      "metadata_sha256": "fc6fd007c09f83d75c59d91668502913f0b4cc34ac77eee4de0aca0f8b6e9858",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19628",
      "published": "2026-10-14T05:56:19Z",
      "updated": "2026-10-14T05:56:19Z",
      "revision": 1,
      "metadata_sha256": "36e1ae0a59f6e022f15f068045d6c433dd92b1e3e68c6452ab5e06f56947f22e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19625",
      "published": "2026-10-14T05:50:21Z",
      "updated": "2026-10-14T05:50:21Z",
      "revision": 1,
      "metadata_sha256": "c53301212738deabc175d6a29f8620ac77bc3292d8afe3aefa7072c8db8d2d26",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19614",
      "published": "2026-10-14T05:36:22Z",
      "updated": "2026-10-14T05:36:22Z",
      "revision": 1,
      "metadata_sha256": "4d47a05f4c63ab39385269f8752d89a9b66c82a48d652118e873b92fc4c2dbc6",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19607",
      "published": "2026-10-14T05:30:25Z",
      "updated": "2026-10-14T05:30:25Z",
      "revision": 1,
      "metadata_sha256": "cce246610a6216ded985ab9bb2dc7c54556fcd9de9b1d82f04aa2299a3a515d3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19605",
      "published": "2026-10-14T05:29:08Z",
      "updated": "2026-10-14T05:29:08Z",
      "revision": 1,
      "metadata_sha256": "282e663010c24c86dbb11a506cc3427f9dfcb5c9ced57dbb9f209c3bfef0299f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19603",
      "published": "2026-10-14T05:23:29Z",
      "updated": "2026-10-14T05:23:29Z",
      "revision": 1,
      "metadata_sha256": "f38c97ad9d9e7a23a0d1a4419e17299f09f55f40db214943af4cdfdf4638c2d6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19601",
      "published": "2026-10-14T05:23:00Z",
      "updated": "2026-10-14T05:23:00Z",
      "revision": 1,
      "metadata_sha256": "7a0b658a51d7a4e5fcda1641c0442ded9330c797578f123dff748cd4ffbfed5b",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19592",
      "published": "2026-10-14T05:09:19Z",
      "updated": "2026-10-14T05:09:19Z",
      "revision": 1,
      "metadata_sha256": "cf59359456cf89e2f2aa8e2d29b9ec2be1b447da84a32a8de6f8bb27b7edc8db",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19591",
      "published": "2026-10-14T05:03:06Z",
      "updated": "2026-10-14T05:03:06Z",
      "revision": 1,
      "metadata_sha256": "6c4f6e6439ee7dca0b7c526975b54dc09c813983393c8f1f4649cb1c356ed675",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19588",
      "published": "2026-10-14T04:59:27Z",
      "updated": "2026-10-14T04:59:27Z",
      "revision": 1,
      "metadata_sha256": "717b3ea03e31fd2009ce5550c2555fb0e236cf4622360e70b38eff4b3543b263",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19583",
      "published": "2026-10-14T04:54:35Z",
      "updated": "2026-10-14T04:54:35Z",
      "revision": 1,
      "metadata_sha256": "e200eb67faf683e02678fa25b87053edac928e37979f6ecef6246be048456488",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19578",
      "published": "2026-10-14T04:43:38Z",
      "updated": "2026-10-14T04:43:38Z",
      "revision": 1,
      "metadata_sha256": "ba12ed0b6e8ea6bf49ce81f162017efe035c2168a022884e281eb32572ca843d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19576",
      "published": "2026-10-14T04:42:30Z",
      "updated": "2026-10-14T04:42:30Z",
      "revision": 1,
      "metadata_sha256": "22a05882722db1773bd431b28994639bf39a4b1efa6a603bd4c2345ed6d84c5a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19573",
      "published": "2026-10-14T04:40:10Z",
      "updated": "2026-10-14T04:40:10Z",
      "revision": 1,
      "metadata_sha256": "e711522bca13cc7cf31eb0ed8a64461b1e3e2af42683f8e667acf2eb2813ffe7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19570",
      "published": "2026-10-14T04:36:02Z",
      "updated": "2026-10-14T04:36:02Z",
      "revision": 1,
      "metadata_sha256": "d8f9aab5d85c550352a3d238f1da69e44f3b78cfdce5f0a6647c46639101da64",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19568",
      "published": "2026-10-14T04:35:34Z",
      "updated": "2026-10-14T04:35:34Z",
      "revision": 1,
      "metadata_sha256": "254345b969473940bb8d1cd93bfd9d7f4f27e25f1359ed025dadf082ed4c6812",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.19560",
      "published": "2026-10-14T04:19:15Z",
      "updated": "2026-10-14T04:19:15Z",
      "revision": 1,
      "metadata_sha256": "b6375d3a78a1b7244204ad8332f7bf346109e379ef805c1c26b049d53acc1dbb",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19557",
      "published": "2026-10-14T04:15:12Z",
      "updated": "2026-10-14T04:15:12Z",
      "revision": 1,
      "metadata_sha256": "782ccb9898930e2119215ce531d10de0806323a8cfeb81cc4ac66365f4331d19",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19556",
      "published": "2026-10-14T04:13:35Z",
      "updated": "2026-10-14T04:13:35Z",
      "revision": 1,
      "metadata_sha256": "f8e5b88b7356a3d1deca669725678be79d4bfc18aebab787a2480663318ffb95",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19552",
      "published": "2026-10-14T04:08:44Z",
      "updated": "2026-10-14T04:08:44Z",
      "revision": 1,
      "metadata_sha256": "11e3adeee4d21e8409799dfa08b822ba563e5697b895203778b918fd56d38421",
      "repository_status": "new",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.19543",
      "published": "2026-10-14T04:02:37Z",
      "updated": "2026-10-14T04:02:37Z",
      "revision": 1,
      "metadata_sha256": "31848dd885959be0c6d852ea70930cbc344c1eaf59503272abc6b9109f0948ba",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19539",
      "published": "2026-10-14T03:57:04Z",
      "updated": "2026-10-14T03:57:04Z",
      "revision": 1,
      "metadata_sha256": "7fe73348f0f38a0951a221219dec833d3bcae29ce2e925ad5b81141035a9c7d4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19536",
      "published": "2026-10-14T03:54:19Z",
      "updated": "2026-10-14T03:54:19Z",
      "revision": 1,
      "metadata_sha256": "1dbc0f22e6cff48cb2455a07579ac9e4df065f94b0d36f160351af3fc7a3f246",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19532",
      "published": "2026-10-14T03:47:20Z",
      "updated": "2026-10-14T03:47:20Z",
      "revision": 1,
      "metadata_sha256": "7897f9d58091c01e5fbcb60b6b4b857d7509f88ff4a482548a71320bdd791858",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19528",
      "published": "2026-10-14T03:45:40Z",
      "updated": "2026-10-14T03:45:40Z",
      "revision": 1,
      "metadata_sha256": "26ec710be3a8a23d3183e5a5560b03f6727561bc1d7d5a9220dd560a5ce95b85",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.19525",
      "published": "2026-10-14T03:42:59Z",
      "updated": "2026-10-14T03:42:59Z",
      "revision": 1,
      "metadata_sha256": "34f401c21faacfee0585a58c923dbdbe8edd0600f35be4649f89cff4a8943e2d",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19524",
      "published": "2026-10-14T03:42:08Z",
      "updated": "2026-10-14T03:42:08Z",
      "revision": 1,
      "metadata_sha256": "64bfe03fca587dafeea6dfd79c720637f7b6b5e7547d8f69bc332a836035c294",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19513",
      "published": "2026-10-14T03:30:45Z",
      "updated": "2026-10-14T03:30:45Z",
      "revision": 1,
      "metadata_sha256": "eda2f9ab3a49acc4e601488f74968860224db4d4b1d7472c17588681bc4c88e5",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19508",
      "published": "2026-10-14T03:25:56Z",
      "updated": "2026-10-14T03:25:56Z",
      "revision": 1,
      "metadata_sha256": "ccb04046f9b16874c2b7e0e90b4123af1605fc14b9dc775abeec642b90a16ef9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19505",
      "published": "2026-10-14T03:22:40Z",
      "updated": "2026-10-14T03:22:40Z",
      "revision": 1,
      "metadata_sha256": "fbe129b6ede9a24f180f29c00735f0b461ab4fcf9582e3a865f4eab873a0819c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19498",
      "published": "2026-10-14T03:16:29Z",
      "updated": "2026-10-14T03:16:29Z",
      "revision": 1,
      "metadata_sha256": "87c17d05aa31fb90dcdcd2d2a2c31e4d63d37fd79c28c56ddf527751311d5187",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19490",
      "published": "2026-10-14T03:11:47Z",
      "updated": "2026-10-14T03:11:47Z",
      "revision": 1,
      "metadata_sha256": "32fd28c077500704f5881f481aa831c231c8579fd86ee1be68606eeb8ebc5936",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19484",
      "published": "2026-10-14T02:59:43Z",
      "updated": "2026-10-14T02:59:43Z",
      "revision": 1,
      "metadata_sha256": "781fca58d6196aa499da489cc2c8e190c9146424fdcc7da977f37a95bc9d6221",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19476",
      "published": "2026-10-14T02:54:57Z",
      "updated": "2026-10-14T02:54:57Z",
      "revision": 1,
      "metadata_sha256": "6fbcdfc1aae140e4d9a86ceca5e88be15962d3a341cf7685d4c189f2b711cdde",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.19475",
      "published": "2026-10-14T02:54:40Z",
      "updated": "2026-10-14T02:54:40Z",
      "revision": 1,
      "metadata_sha256": "fe8bf1f9e4325e8821e82d77ef419e3507eb8308b6fc2130956a717409bd3c7f",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.19457",
      "published": "2026-10-14T02:42:13Z",
      "updated": "2026-10-14T02:42:13Z",
      "revision": 1,
      "metadata_sha256": "8f7c5b03d4b9d4da2d27b5fc653ff40daaf14516e3ded59c218b9d0bcf6a6a9d",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19444",
      "published": "2026-10-14T02:34:06Z",
      "updated": "2026-10-14T02:34:06Z",
      "revision": 1,
      "metadata_sha256": "660d46a860dec24d185c773cc064b41f213f5907acd624eeed9139cc8397f39c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19439",
      "published": "2026-10-14T02:31:56Z",
      "updated": "2026-10-14T02:31:56Z",
      "revision": 1,
      "metadata_sha256": "266ca2f355e3fd6020b6a93f4360eb8a02d82dde5d11168721b714510b6f961c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19436",
      "published": "2026-10-14T02:28:39Z",
      "updated": "2026-10-14T02:28:39Z",
      "revision": 1,
      "metadata_sha256": "33d493e4970b872f1221227ab4fabe5bd5e5cc683fede75049768144b35bb40b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19429",
      "published": "2026-10-14T02:25:17Z",
      "updated": "2026-10-14T02:25:17Z",
      "revision": 1,
      "metadata_sha256": "257272ba51abf801bcba7b48de5e4a271d466f0aded7d6f8b4716f525d2513be",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19411",
      "published": "2026-10-14T01:58:40Z",
      "updated": "2026-10-14T01:58:40Z",
      "revision": 1,
      "metadata_sha256": "842449c8d77da979632b1bc8bd8ef1dcb7342832146971e325ebeae16b56e524",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19408",
      "published": "2026-10-14T01:56:46Z",
      "updated": "2026-10-14T01:56:46Z",
      "revision": 1,
      "metadata_sha256": "92536affb2c281c50e1c37e740aacdfbf9f8fc5b6a1c77fe3c4068eb30314554",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19405",
      "published": "2026-10-14T01:53:24Z",
      "updated": "2026-10-14T01:53:24Z",
      "revision": 1,
      "metadata_sha256": "11c21c44a440e43633f1e571ab69179d5e4adbfb2a462b3bc0a15498742b6d42",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19404",
      "published": "2026-10-14T01:52:55Z",
      "updated": "2026-10-14T01:52:55Z",
      "revision": 1,
      "metadata_sha256": "d080d784400e1b8e4850fb935f33981dbd753e18fe08b8ad4393249023859e75",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19401",
      "published": "2026-10-14T01:49:40Z",
      "updated": "2026-10-14T01:49:40Z",
      "revision": 1,
      "metadata_sha256": "2866bb02c4e8fc6e1a3ae78597687f95a3e4cd794209b0cbee895e075f5aae4a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19394",
      "published": "2026-10-14T01:39:56Z",
      "updated": "2026-10-14T01:39:56Z",
      "revision": 1,
      "metadata_sha256": "46f334dfd2ea5cb3242550a8267f40a74c606e53a6b641975f0e1b4c21e5adba",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19391",
      "published": "2026-10-14T01:35:33Z",
      "updated": "2026-10-14T01:35:33Z",
      "revision": 1,
      "metadata_sha256": "95eb509c13aedb3d9919122577f7b5d6e6cf1d4e94c14c3b64cedab02dec24cf",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19385",
      "published": "2026-10-14T01:31:40Z",
      "updated": "2026-10-14T01:31:40Z",
      "revision": 1,
      "metadata_sha256": "c2368bc6e3974c0458791264cf3cbdc2b21cb5b6bf735e988b14ecadc546fa1c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19380",
      "published": "2026-10-14T01:27:19Z",
      "updated": "2026-10-14T01:27:19Z",
      "revision": 1,
      "metadata_sha256": "efab763971201741303c41139a99e2865d0009bc4f930797aab7a61540bfebe5",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19378",
      "published": "2026-10-14T01:24:53Z",
      "updated": "2026-10-14T01:24:53Z",
      "revision": 1,
      "metadata_sha256": "339b0242192e783fadbf196862b75bd89c5cbb4ba5fdc2ca9d8cdd3a1d17146f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19375",
      "published": "2026-10-14T01:19:50Z",
      "updated": "2026-10-14T01:19:50Z",
      "revision": 1,
      "metadata_sha256": "8b5dd7a3e51cd9c5a89f3aa66f6f83f074cb3859927de7bf2aa89866ec0b3a13",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19372",
      "published": "2026-10-14T01:16:15Z",
      "updated": "2026-10-14T01:16:15Z",
      "revision": 1,
      "metadata_sha256": "b5282838db7a0b62ef9ed83e16fb963f546530e56eabfa96c0cffe536a9c847c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19369",
      "published": "2026-10-14T01:12:58Z",
      "updated": "2026-10-14T01:12:58Z",
      "revision": 1,
      "metadata_sha256": "10bb2e9999446645dca1fbbac6646cc8ea722a743c41b9d796b69e412942acb9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19367",
      "published": "2026-10-14T01:12:03Z",
      "updated": "2026-10-14T01:12:03Z",
      "revision": 1,
      "metadata_sha256": "0634497ba426b0da540a9616e566318e6198a151ac38dcafe62263d33c5f7439",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.19364",
      "published": "2026-10-14T01:09:47Z",
      "updated": "2026-10-14T01:09:47Z",
      "revision": 1,
      "metadata_sha256": "e98e5e8787e43a171f3eaed6435e06107d0ccc6a632c828e77cbe92f053256f4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19362",
      "published": "2026-10-14T01:09:16Z",
      "updated": "2026-10-14T01:09:16Z",
      "revision": 1,
      "metadata_sha256": "1c53d48b0900792da2c78860dcf3ce49e5eb6f122c1899d4015c240da172c30b",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19359",
      "published": "2026-10-14T01:00:35Z",
      "updated": "2026-10-14T01:00:35Z",
      "revision": 1,
      "metadata_sha256": "4dc4fc5bc5db6a3c91bf825184d897432a1b5e8bb19f0f47baf6d31066fc0ff8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19358",
      "published": "2026-10-14T00:59:20Z",
      "updated": "2026-10-14T00:59:20Z",
      "revision": 1,
      "metadata_sha256": "076a5cc9eea4f0e88b51ed2c23b5f10c5830cd8bbbbcf779f7b4ad768186acd9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19352",
      "published": "2026-10-14T00:52:39Z",
      "updated": "2026-10-14T00:52:39Z",
      "revision": 1,
      "metadata_sha256": "1033dd4221641d6d2fb5588632964f752544e7d742582865727a7418235dfcaa",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19349",
      "published": "2026-10-14T00:42:53Z",
      "updated": "2026-10-14T00:42:53Z",
      "revision": 1,
      "metadata_sha256": "3a1fd3f4882f210087195626eae6b8722a7d299f711863e4d420c9f9ee2d1113",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19347",
      "published": "2026-10-14T00:41:14Z",
      "updated": "2026-10-14T00:41:14Z",
      "revision": 1,
      "metadata_sha256": "cc016ee49d7d716dfe022b0df72b0d89de12bdeecaf058de8d97dd103bc155e9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19344",
      "published": "2026-10-14T00:36:45Z",
      "updated": "2026-10-14T00:36:45Z",
      "revision": 1,
      "metadata_sha256": "7d58f145aa5d18c450e04a45defdf8bd2551f95b0374027b7ba09a6b1156cbcf",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19343",
      "published": "2026-10-14T00:36:40Z",
      "updated": "2026-10-14T00:36:40Z",
      "revision": 1,
      "metadata_sha256": "5084a472c0b0bf8f128bb16ac6cbf176eb11980e7f86d52b8fdd0807459272aa",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19324",
      "published": "2026-10-14T00:02:42Z",
      "updated": "2026-10-14T00:02:42Z",
      "revision": 1,
      "metadata_sha256": "b9204f71d20f2a85aba1dc066db3ee73de4d96198432d87ecc98e6006f983fb3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19323",
      "published": "2026-10-14T00:01:35Z",
      "updated": "2026-10-14T00:01:35Z",
      "revision": 1,
      "metadata_sha256": "12696d4b9c7b16ba06a4282a3b53f3e9c22d34d5f6772911e8d45e39289d326e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19315",
      "published": "2026-10-13T23:57:28Z",
      "updated": "2026-10-13T23:57:28Z",
      "revision": 1,
      "metadata_sha256": "b84eaf97898fe0b26b30b2fcc190ee4c9dcf1c20579a640650872daf9b770892",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19306",
      "published": "2026-10-13T23:32:17Z",
      "updated": "2026-10-13T23:32:17Z",
      "revision": 1,
      "metadata_sha256": "d6f3704644efce7e78120c013d744ec170f45389875f027e7e41245c8afe6643",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19302",
      "published": "2026-10-13T23:26:26Z",
      "updated": "2026-10-13T23:26:26Z",
      "revision": 1,
      "metadata_sha256": "5b963e2c68366941b38e00825efe9ac10414938f1a2e72a5b67da76e83d64c5a",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19298",
      "published": "2026-10-13T23:17:25Z",
      "updated": "2026-10-13T23:17:25Z",
      "revision": 1,
      "metadata_sha256": "2af8f8ce20f34114717924669d737e84c4c804ab238136fa0f9e1d906ab7292f",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.19281",
      "published": "2026-10-13T23:02:10Z",
      "updated": "2026-10-13T23:02:10Z",
      "revision": 1,
      "metadata_sha256": "a7804abe223f13544843530942aa50e54fbdbbd9096b3ca04fb97b21b8c101fd",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19279",
      "published": "2026-10-13T22:55:32Z",
      "updated": "2026-10-13T22:55:32Z",
      "revision": 1,
      "metadata_sha256": "2eccce2e2607f43befd08e28925fad4ce4bb4bb9c20c658b7344fd223295e2b0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19271",
      "published": "2026-10-13T22:44:18Z",
      "updated": "2026-10-13T22:44:18Z",
      "revision": 1,
      "metadata_sha256": "b5332264243624e0f71e43211fed0c1122bdb8b28ac22d8b3d637a5a463657a7",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19270",
      "published": "2026-10-13T22:44:10Z",
      "updated": "2026-10-13T22:44:10Z",
      "revision": 1,
      "metadata_sha256": "03efd65ae1486d47e060fba8600b96d78e06bf66bab3ed634ba115c1965452e0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19254",
      "published": "2026-10-13T22:15:06Z",
      "updated": "2026-10-13T22:15:06Z",
      "revision": 1,
      "metadata_sha256": "cf1f28db609d5f9bc414c7be4fd68458a0858637d7fc83dc5db805835ffee995",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19252",
      "published": "2026-10-13T22:13:30Z",
      "updated": "2026-10-13T22:13:30Z",
      "revision": 1,
      "metadata_sha256": "4b4172f3aefc08331bc11e006158880cf6c219c2c534fcd8cf2f6178da1b321b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19246",
      "published": "2026-10-13T22:01:49Z",
      "updated": "2026-10-13T22:01:49Z",
      "revision": 1,
      "metadata_sha256": "2551fe19c66833f165febf4297ea99403f8b50c1b549fde72b7705c9272060d3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19240",
      "published": "2026-10-13T21:57:50Z",
      "updated": "2026-10-13T21:57:50Z",
      "revision": 1,
      "metadata_sha256": "8d4c6b947b0ae663347eccef12b6b5f3b0dc9066686c79c326c06a46d9545f11",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19238",
      "published": "2026-10-13T21:56:45Z",
      "updated": "2026-10-13T21:56:45Z",
      "revision": 1,
      "metadata_sha256": "10aae89839e6f9384a08ab440a388bb49343cd42812b052fe8ebbe033860de6a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19235",
      "published": "2026-10-13T21:52:59Z",
      "updated": "2026-10-13T21:52:59Z",
      "revision": 1,
      "metadata_sha256": "4fec1d9c7b17a6337d43ad5462c9df793cb4c12395586c2376578e7484d6890c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19232",
      "published": "2026-10-13T21:48:12Z",
      "updated": "2026-10-13T21:48:12Z",
      "revision": 1,
      "metadata_sha256": "d03496fcb0c229148c66b377486fd545c6f17716b5bc3fd161872cab44f1f290",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19220",
      "published": "2026-10-13T21:36:28Z",
      "updated": "2026-10-13T21:36:28Z",
      "revision": 1,
      "metadata_sha256": "14a6d1d340a016da10bf0cda0b4a7d5bade7d3650cddb4970a5082c1e6437548",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19215",
      "published": "2026-10-13T21:27:48Z",
      "updated": "2026-10-13T21:27:48Z",
      "revision": 1,
      "metadata_sha256": "37435abee90ce39955d4db4a88afb92d82de58cbb373ea2f42b471aa98537cec",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.19211",
      "published": "2026-10-13T21:24:01Z",
      "updated": "2026-10-13T21:24:01Z",
      "revision": 1,
      "metadata_sha256": "ec2ba5f52c28a10fb5c6291e6e5f6a8ac7d6fd7e578691e2d7f98e7b900e625a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19210",
      "published": "2026-10-13T21:23:58Z",
      "updated": "2026-10-13T21:23:58Z",
      "revision": 1,
      "metadata_sha256": "10dabe96e54f5ea720d27f64f3bfdc8c701ea998ec8aba4dfdc7fb5e79219c5e",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.19198",
      "published": "2026-10-13T21:03:50Z",
      "updated": "2026-10-13T21:03:50Z",
      "revision": 1,
      "metadata_sha256": "1a7a72904c4d04cdee3cda099d4e7ac2ad40c8ca14b0f34c8acce286b3b80208",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19191",
      "published": "2026-10-13T20:55:03Z",
      "updated": "2026-10-13T20:55:03Z",
      "revision": 1,
      "metadata_sha256": "2a936dd86bd096e23cbe165c973f5dd29b4b3e5400e8f282757e133c0c1a9940",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19189",
      "published": "2026-10-13T20:53:42Z",
      "updated": "2026-10-13T20:53:42Z",
      "revision": 1,
      "metadata_sha256": "29c76f386ca714fc2428db65bfe777e0ace984b458dc5073bb79fc293ce269f2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19187",
      "published": "2026-10-13T20:52:11Z",
      "updated": "2026-10-13T20:52:11Z",
      "revision": 1,
      "metadata_sha256": "4e2331a7727873d96dcbf0a58c8fa08d041c2690057110649998d3db11ef6887",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19179",
      "published": "2026-10-13T20:45:13Z",
      "updated": "2026-10-13T20:45:13Z",
      "revision": 1,
      "metadata_sha256": "5ed0bbb7af98686dc1a88b47c414d7d74b4b6a6c84e08cd166cee92b89464fe7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19178",
      "published": "2026-10-13T20:44:03Z",
      "updated": "2026-10-13T20:44:03Z",
      "revision": 1,
      "metadata_sha256": "668be9f6c26ef41aa9311e34e885d455ad0062746df5107fd5cf56aa37d75f59",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19159",
      "published": "2026-10-13T20:25:59Z",
      "updated": "2026-10-13T20:25:59Z",
      "revision": 1,
      "metadata_sha256": "58339831858aa91dc9d058815e329a28f00c4eabdc5254bd2f734e8d0fb729c0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19145",
      "published": "2026-10-13T20:11:48Z",
      "updated": "2026-10-13T20:11:48Z",
      "revision": 1,
      "metadata_sha256": "cbd93aa9eecf4eebf80b7190d61671fdb0be5413c2c409cf0415d768df79118b",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19142",
      "published": "2026-10-13T20:09:27Z",
      "updated": "2026-10-13T20:09:27Z",
      "revision": 1,
      "metadata_sha256": "d3f004e4856942ba7dfced5a5785572d37c83ca970833d23136ddd98df2bb770",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19139",
      "published": "2026-10-13T20:08:40Z",
      "updated": "2026-10-13T20:08:40Z",
      "revision": 1,
      "metadata_sha256": "fd38b34f9b0e6d662a56efdfeb935bd0a366ffee906eb5ec3764c79b87f4cd50",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19138",
      "published": "2026-10-13T20:07:50Z",
      "updated": "2026-10-13T20:07:50Z",
      "revision": 1,
      "metadata_sha256": "7c3c7cba8acd8f2e3ca3ce20fe076a7c95049a15018a985d9a5a2f861f0c13d9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19135",
      "published": "2026-10-13T20:05:44Z",
      "updated": "2026-10-13T20:05:44Z",
      "revision": 1,
      "metadata_sha256": "f8e2e42bfacfc777ea30a8d796a8241014317c451aece6412f8ee2c40cde1e0f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19133",
      "published": "2026-10-13T20:03:37Z",
      "updated": "2026-10-13T20:03:37Z",
      "revision": 1,
      "metadata_sha256": "8909ab74a80bfeaa41532c121d398355acd145951c4c26395c37d70b65fcde02",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19129",
      "published": "2026-10-13T20:02:11Z",
      "updated": "2026-10-13T20:02:11Z",
      "revision": 1,
      "metadata_sha256": "b1b39e14de018725b37e799dc1e944e0a4a6652af0b406732ec87c4e5acc010e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19123",
      "published": "2026-10-13T19:57:58Z",
      "updated": "2026-10-13T19:57:58Z",
      "revision": 1,
      "metadata_sha256": "ba8641c5a574908810eb2ad8c6393eb3939427b381f63f8412786f52dab795b4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19121",
      "published": "2026-10-13T19:55:33Z",
      "updated": "2026-10-13T19:55:33Z",
      "revision": 1,
      "metadata_sha256": "9ac93c122af7f83b0b9d73e787219db50303b8cfd49f998b00923e3ba1a5eae0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19114",
      "published": "2026-10-13T19:51:03Z",
      "updated": "2026-10-13T19:51:03Z",
      "revision": 1,
      "metadata_sha256": "86bb9e89d8c24e861ef9f7d0a03ea53fdeb84d9bc0445b2b5a9a92edb5017f55",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19113",
      "published": "2026-10-13T19:49:33Z",
      "updated": "2026-10-13T19:49:33Z",
      "revision": 1,
      "metadata_sha256": "9d3d4dca63cd037f39142728b19d405c994a76e5cd347d60cfcf577745ebdb4e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19108",
      "published": "2026-10-13T19:42:30Z",
      "updated": "2026-10-13T19:42:30Z",
      "revision": 1,
      "metadata_sha256": "08cf9421caf2db015677fecf80fcad8773c89cdebe066c42bbc97cdcf3f2ea23",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.19104",
      "published": "2026-10-13T19:40:08Z",
      "updated": "2026-10-13T19:40:08Z",
      "revision": 1,
      "metadata_sha256": "144bf05e3a356b2dae916a1e5a77c85d83fd86473f15ea01a7a2eff8022e996d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19103",
      "published": "2026-10-13T19:39:52Z",
      "updated": "2026-10-13T19:39:52Z",
      "revision": 1,
      "metadata_sha256": "04510cb06f95438e1d1281d013ebaf3a519f79a7a9b66ede7adf596fbdf57ff1",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.19100",
      "published": "2026-10-13T19:37:49Z",
      "updated": "2026-10-13T19:37:49Z",
      "revision": 1,
      "metadata_sha256": "d0b5a2670eb0979fa521efc8fcec28345f35aa2f3d06cd599f42248f90fab0f4",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19095",
      "published": "2026-10-13T19:33:25Z",
      "updated": "2026-10-13T19:33:25Z",
      "revision": 1,
      "metadata_sha256": "acda0cb8eb750e4f626d3b75697418bc54dd5e5bb2fb3e86fecf1f128f8606ba",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19084",
      "published": "2026-10-13T19:15:06Z",
      "updated": "2026-10-13T19:15:06Z",
      "revision": 1,
      "metadata_sha256": "26bfba5f77ae38e98e47853f8f48acba15c36ed85af2c88dbd79fadbc01e298a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19080",
      "published": "2026-10-13T19:12:33Z",
      "updated": "2026-10-13T19:12:33Z",
      "revision": 1,
      "metadata_sha256": "b50d255b458a62c106ba80396d860d773809c3e01439d6d436fa2861fb22eaf5",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.19074",
      "published": "2026-10-13T19:08:56Z",
      "updated": "2026-10-13T19:08:56Z",
      "revision": 1,
      "metadata_sha256": "1852daaf8e83f711e77de7e97d182c7b6417f9b291d93944e78ab8f13455380b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19065",
      "published": "2026-10-13T19:02:30Z",
      "updated": "2026-10-13T19:02:30Z",
      "revision": 1,
      "metadata_sha256": "15a749762d10a1c5f206ee06f5ed1d5ded96ff92c1b5f8eea8011c7d16452ebd",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19064",
      "published": "2026-10-13T19:00:27Z",
      "updated": "2026-10-13T19:00:27Z",
      "revision": 1,
      "metadata_sha256": "0b059515bb05d7db7f4fb107331de1dcf6c75f65274bfd5a30522095db4f27fb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19058",
      "published": "2026-10-13T18:55:22Z",
      "updated": "2026-10-13T18:55:22Z",
      "revision": 1,
      "metadata_sha256": "e46412a57e4cf702856159769ba97a38f6f0a280cb94350696096969d8628fa6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19053",
      "published": "2026-10-13T18:52:26Z",
      "updated": "2026-10-13T18:52:26Z",
      "revision": 1,
      "metadata_sha256": "43e8bf2efc6411c744d9e6897c790f2413f3584b1c0439d8d6cd366c55710438",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19051",
      "published": "2026-10-13T18:50:10Z",
      "updated": "2026-10-13T18:50:10Z",
      "revision": 1,
      "metadata_sha256": "253451959d73d8df5d518b5191b7c5c1c833f058acb03d018daee0f432b51666",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19046",
      "published": "2026-10-13T18:40:53Z",
      "updated": "2026-10-13T18:40:53Z",
      "revision": 1,
      "metadata_sha256": "5734792e0103322d12a345154a5789acc515248bed5969f6fa629d598a437d36",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19043",
      "published": "2026-10-13T18:32:31Z",
      "updated": "2026-10-13T18:32:31Z",
      "revision": 1,
      "metadata_sha256": "d8a089887bc8b3c12fde8face58d40cbf3952928ba3e585d1329b06972a198f9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19042",
      "published": "2026-10-13T18:31:16Z",
      "updated": "2026-10-13T18:31:16Z",
      "revision": 1,
      "metadata_sha256": "fb57e6e6e12a525ef1776b251fe55e364165777e4f197c4ef7cd5b26c753283d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19041",
      "published": "2026-10-13T18:29:52Z",
      "updated": "2026-10-13T18:29:52Z",
      "revision": 1,
      "metadata_sha256": "b4fa937aa59d6814251cc992dc302e596b2d0e013e41dea86fc30c68c661de10",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19038",
      "published": "2026-10-13T18:28:08Z",
      "updated": "2026-10-13T18:28:08Z",
      "revision": 1,
      "metadata_sha256": "d96fe6abf7b480305e14a18286d308ded7387582174d5196733641042c664449",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19035",
      "published": "2026-10-13T18:27:17Z",
      "updated": "2026-10-13T18:27:17Z",
      "revision": 1,
      "metadata_sha256": "571610cd6e98fa6c6aaf5b6217914e2b10d93710a581c307af8787553d14b485",
      "repository_status": "new",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.19033",
      "published": "2026-10-13T18:26:50Z",
      "updated": "2026-10-13T18:26:50Z",
      "revision": 1,
      "metadata_sha256": "8f8ec3f3b4586d0f7a8eb135bcb7a0f8457b4d2cfe514560520b01677bffd326",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19027",
      "published": "2026-10-13T18:20:29Z",
      "updated": "2026-10-13T18:20:29Z",
      "revision": 1,
      "metadata_sha256": "1e6f41a6979d3836e6f3106d4b2acc56dda2f9112badbce16ec5030089471f35",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19025",
      "published": "2026-10-13T18:18:41Z",
      "updated": "2026-10-13T18:18:41Z",
      "revision": 1,
      "metadata_sha256": "b430d48b067756f905cfd0766db017b63a439bae9b4b6932b7f8c202521142fe",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19020",
      "published": "2026-10-13T18:12:59Z",
      "updated": "2026-10-13T18:12:59Z",
      "revision": 1,
      "metadata_sha256": "61354269187eb3e8a526f930c7f122da5217f3ef0d89ac64059351986b727cb6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19016",
      "published": "2026-10-13T18:10:11Z",
      "updated": "2026-10-13T18:10:11Z",
      "revision": 1,
      "metadata_sha256": "0bde7201f47ca1e9c3c37a2f92985d19ba3dde4655c76a68c26fe6bd682b9002",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19015",
      "published": "2026-10-13T18:09:45Z",
      "updated": "2026-10-13T18:09:45Z",
      "revision": 1,
      "metadata_sha256": "ebb1e857752c0f938406af6dcd3407264c62abcae60c9ce47720221745c2eb50",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19013",
      "published": "2026-10-13T18:08:51Z",
      "updated": "2026-10-13T18:08:51Z",
      "revision": 1,
      "metadata_sha256": "ca0436105baa33df9a7b48e470a6ffb40b67a9e932f012892cd5ff514d50ee5f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.19011",
      "published": "2026-10-13T18:07:37Z",
      "updated": "2026-10-13T18:07:37Z",
      "revision": 1,
      "metadata_sha256": "9a756bb8d835de6fcfb29aa64c63db0b66f9c64461657dff1a57e6bd7c58499a",
      "repository_status": "new",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.18990",
      "published": "2026-10-13T18:00:42Z",
      "updated": "2026-10-13T18:00:42Z",
      "revision": 1,
      "metadata_sha256": "fc626e6d25b7b2abbf3080588a500d417e3137cde86b3b715b955ca0fbce4f2a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18869",
      "published": "2026-10-13T17:59:52Z",
      "updated": "2026-10-13T17:59:52Z",
      "revision": 1,
      "metadata_sha256": "7ecd0626e56be8563fab9a029c53e60599798d41756c0198e742fc7b1e0098d0",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18868",
      "published": "2026-10-13T17:59:51Z",
      "updated": "2026-10-13T17:59:51Z",
      "revision": 1,
      "metadata_sha256": "e92f160d3eec6cb12d3cabb724c0e9bc40aa170d395e02d0cabb04832dc7121f",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18861",
      "published": "2026-10-13T17:59:31Z",
      "updated": "2026-10-13T17:59:31Z",
      "revision": 1,
      "metadata_sha256": "9f98e83ffdda40f482e573e8b97e06724f65f5561125c9d67aeff24ee169557d",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.18853",
      "published": "2026-10-13T17:58:57Z",
      "updated": "2026-10-13T17:58:57Z",
      "revision": 1,
      "metadata_sha256": "27d94cdc485d8b5869519163ee2769e2f903b3745af8c795ce58da6edef53736",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18851",
      "published": "2026-10-13T17:58:41Z",
      "updated": "2026-10-13T17:58:41Z",
      "revision": 1,
      "metadata_sha256": "312cb2b7efe1de586195d63ad04794473260f9e3c5f5835f8bbf96b658f6615f",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18835",
      "published": "2026-10-13T17:55:14Z",
      "updated": "2026-10-14T17:02:18Z",
      "revision": 2,
      "metadata_sha256": "947f1f5fe7869ae8c2a3c8ffeaec25007fab5da714260cd94ef8798e3501028a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18807",
      "published": "2026-10-13T17:46:25Z",
      "updated": "2026-10-13T17:46:25Z",
      "revision": 1,
      "metadata_sha256": "6e1e75df72a973c537b4629f2f9465836471a8e771f8dfa90cf2dea38b9ed32c",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18766",
      "published": "2026-10-13T17:27:23Z",
      "updated": "2026-10-13T17:27:23Z",
      "revision": 1,
      "metadata_sha256": "67bd58328a9c4a2424193584f9592a6fe909fbd6c639b2148a915754aa5272f0",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation",
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18755",
      "published": "2026-10-13T17:19:10Z",
      "updated": "2026-10-13T17:19:10Z",
      "revision": 1,
      "metadata_sha256": "943a8ea2a180109ef8b721e1ab66ee3e09936c69a722f6b029b200512e077e16",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18738",
      "published": "2026-10-13T17:09:23Z",
      "updated": "2026-10-13T17:09:23Z",
      "revision": 1,
      "metadata_sha256": "d0ea3f5c41fd220a9d8026d998da8e084260e1824175ce56e64e96e63ca128c2",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.18695",
      "published": "2026-10-13T16:46:34Z",
      "updated": "2026-10-13T16:46:34Z",
      "revision": 1,
      "metadata_sha256": "e0ec0377be6a6cc134fc780ece029bd420153ef2cdd8087b60bc77b4c840a1ea",
      "repository_status": "new",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.18683",
      "published": "2026-10-13T16:39:38Z",
      "updated": "2026-10-13T16:39:38Z",
      "revision": 1,
      "metadata_sha256": "d9cf0aacb3627a27a39b008e3061cf751a89adb3d358ec239956e7a34e2d925b",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "preference-optimization",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18949",
      "published": "2026-10-13T16:24:49Z",
      "updated": "2026-10-13T16:24:49Z",
      "revision": 1,
      "metadata_sha256": "32024955666c14d65c897835039cee6e8b992a23f78c19ce502b8aad88518c08",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18651",
      "published": "2026-10-13T16:14:35Z",
      "updated": "2026-10-14T17:58:29Z",
      "revision": 2,
      "metadata_sha256": "16b726a6d51002264a48053eaab7bed4e37cb0ddb538dddb8102382b2e2a81d8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18642",
      "published": "2026-10-13T16:10:45Z",
      "updated": "2026-10-13T16:10:45Z",
      "revision": 1,
      "metadata_sha256": "1488ed24ea0b77dae7626a2fa5b8590e36a1134298ca4c4678cab9fdf4c92070",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18614",
      "published": "2026-10-13T16:00:01Z",
      "updated": "2026-10-13T16:00:01Z",
      "revision": 1,
      "metadata_sha256": "95ac6f8fcf6e1addf64a85b90635bd4c4131202663f871b3721e98c73a339617",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18613",
      "published": "2026-10-13T15:59:36Z",
      "updated": "2026-10-13T15:59:36Z",
      "revision": 1,
      "metadata_sha256": "63d82e15e00a70e47d560155648ab8047786befade196847f53b0ee05a5ad078",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18948",
      "published": "2026-10-13T15:49:55Z",
      "updated": "2026-10-13T15:49:55Z",
      "revision": 1,
      "metadata_sha256": "5a74d05062c25d5eeb15b7aa0710f15a463f42d0907784643f7d7e9895c514e8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18572",
      "published": "2026-10-13T15:39:34Z",
      "updated": "2026-10-13T15:39:34Z",
      "revision": 1,
      "metadata_sha256": "7b34ca962612544490cee7aa5204c00c6790ab41208ef0d9a563c16582254c69",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.18517",
      "published": "2026-10-13T15:09:59Z",
      "updated": "2026-10-13T15:09:59Z",
      "revision": 1,
      "metadata_sha256": "8581ee21bc4b8f552bfacecaf6d5521ca887ccc1e0739c775a1f1156e69c542f",
      "repository_status": "new",
      "matched_queries": [
        "post-training",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.18946",
      "published": "2026-10-13T15:04:58Z",
      "updated": "2026-10-13T15:04:58Z",
      "revision": 1,
      "metadata_sha256": "6d3a6fb831bc4103125364bd0320b1f8d40c6786bc2a0ae3fae61fa7e7217202",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18945",
      "published": "2026-10-13T15:01:43Z",
      "updated": "2026-10-13T15:01:43Z",
      "revision": 1,
      "metadata_sha256": "8c30084dd4cb9d1fa3c3b7f2bb979aa9bfefe72d0bcacd793e7b370bb1cd8c78",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18504",
      "published": "2026-10-13T14:58:27Z",
      "updated": "2026-10-13T14:58:27Z",
      "revision": 1,
      "metadata_sha256": "ed1e020fcbf0b5305da99ad2983bf8226c737cb7d7938d8064d56ca21cd23d96",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18484",
      "published": "2026-10-13T14:44:24Z",
      "updated": "2026-10-13T14:44:24Z",
      "revision": 1,
      "metadata_sha256": "47012071adeb87cd0421e7c37631c32db2c57189c94f1497484c7c341490c823",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18472",
      "published": "2026-10-13T14:35:46Z",
      "updated": "2026-10-13T14:35:46Z",
      "revision": 1,
      "metadata_sha256": "510ef758ec7dea01c3a6a1d95b8c741871429518bcf9ad89d239b36970e3529e",
      "repository_status": "new",
      "matched_queries": [
        "opd"
      ]
    },
    {
      "arxiv_id": "2610.18462",
      "published": "2026-10-13T14:28:22Z",
      "updated": "2026-10-14T16:27:58Z",
      "revision": 2,
      "metadata_sha256": "15ebffe589e78373dc9c2d9a1c0f877722a474ae029b00143608d4a9bff15cb9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18459",
      "published": "2026-10-13T14:26:41Z",
      "updated": "2026-10-13T14:26:41Z",
      "revision": 1,
      "metadata_sha256": "be7175451cda096271b2d80d6415837cfe3a3efe4bc572f5f25ed637ac351bfc",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18457",
      "published": "2026-10-13T14:24:26Z",
      "updated": "2026-10-13T14:24:26Z",
      "revision": 1,
      "metadata_sha256": "609a14f10de4abe6dc74c02a7d2fce3b5a7e55f280b4bb9fe93dc00ad0a15f35",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18442",
      "published": "2026-10-13T14:16:38Z",
      "updated": "2026-10-13T14:16:38Z",
      "revision": 1,
      "metadata_sha256": "08e19418c25119d14b0d14f53fcb9787a2d05454f33a076e99bbd9c2b399fa36",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18434",
      "published": "2026-10-13T14:10:35Z",
      "updated": "2026-10-14T08:02:29Z",
      "revision": 2,
      "metadata_sha256": "42d40e523cec3109f0c0f4b129e9b7d7dedd674a300dca5b13b16a06077f346a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18415",
      "published": "2026-10-13T13:54:51Z",
      "updated": "2026-10-13T13:54:51Z",
      "revision": 1,
      "metadata_sha256": "2b146feab08348b92c1416a8a9a7017923be9d03b292bbe6b521fbe99994e568",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "preference-optimization",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18939",
      "published": "2026-10-13T13:23:09Z",
      "updated": "2026-10-13T13:23:09Z",
      "revision": 1,
      "metadata_sha256": "25a10e4df1850d85b9d9bd6ea85b72c4ae3ea70dd51dbcda126f26e09309c63d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18343",
      "published": "2026-10-13T13:15:59Z",
      "updated": "2026-10-13T13:15:59Z",
      "revision": 1,
      "metadata_sha256": "179343fee376878254ff65ed7d5133214e42b49dbbd788fa72d7e1694e5556ba",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.18326",
      "published": "2026-10-13T13:03:37Z",
      "updated": "2026-10-13T13:03:37Z",
      "revision": 1,
      "metadata_sha256": "677d7a6488545690ec7f7ad1038db4123f72a771c4e943d96a017ae9809fd457",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18309",
      "published": "2026-10-13T12:52:47Z",
      "updated": "2026-10-13T12:52:47Z",
      "revision": 1,
      "metadata_sha256": "d7d5b11f5470385e82fc5d6599ab10e3b58b5eb940aa9988c584ba3f638558f4",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18299",
      "published": "2026-10-13T12:47:13Z",
      "updated": "2026-10-13T12:47:13Z",
      "revision": 1,
      "metadata_sha256": "699de6cbc0941f02ac31a34e0154a52a4a2212c274a776a29a862295e8f56de7",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18938",
      "published": "2026-10-13T12:46:49Z",
      "updated": "2026-10-13T12:46:49Z",
      "revision": 1,
      "metadata_sha256": "178c719aa9851d2e625b455b674b7862e45c0bec9ec45b0e74ce9a19ac5991b7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18256",
      "published": "2026-10-13T12:22:54Z",
      "updated": "2026-10-13T12:22:54Z",
      "revision": 1,
      "metadata_sha256": "326264972c41d31956562b6802611fccab2ad69963afd16839dca95f90227b62",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18216",
      "published": "2026-10-13T11:47:32Z",
      "updated": "2026-10-13T11:47:32Z",
      "revision": 1,
      "metadata_sha256": "32889e33d065c3f6f22267d935799e315f6de0210c0a63d92a76aba3db3028b1",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18935",
      "published": "2026-10-13T11:42:10Z",
      "updated": "2026-10-13T11:42:10Z",
      "revision": 1,
      "metadata_sha256": "f8e8c9deae9af8d0f7246442b8917d488e31566fba15459e589e5dcfab3e3a29",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18934",
      "published": "2026-10-13T11:41:04Z",
      "updated": "2026-10-13T11:41:04Z",
      "revision": 1,
      "metadata_sha256": "d5c406bbe70fb1a523c0e7f17696693c629de53b9cab17507ba0f4cbeefcb687",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18200",
      "published": "2026-10-13T11:37:04Z",
      "updated": "2026-10-13T11:37:04Z",
      "revision": 1,
      "metadata_sha256": "fc5b7f21209c41bbbc9b3a3766d05cd65e53c974efa2f6a18327deb43233a357",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18933",
      "published": "2026-10-13T11:28:03Z",
      "updated": "2026-10-13T11:28:03Z",
      "revision": 1,
      "metadata_sha256": "b192eec70e076153e1c8362075e527f6914e4eabc610688ce23d42cf443d8e65",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18162",
      "published": "2026-10-13T11:07:04Z",
      "updated": "2026-10-13T11:07:04Z",
      "revision": 1,
      "metadata_sha256": "871d49713df209dd8a4a2589d48a034e0d80b59a9b0a0c48babba25f39aeec09",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.18088",
      "published": "2026-10-13T10:09:15Z",
      "updated": "2026-10-14T05:39:11Z",
      "revision": 2,
      "metadata_sha256": "90bf4400f2cbef5b9fc2df129ca95929d69a725b888b82752fc2c04b32c80f4b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18082",
      "published": "2026-10-13T10:05:06Z",
      "updated": "2026-10-13T10:05:06Z",
      "revision": 1,
      "metadata_sha256": "abb69b39db6823800f9d2e807d821f2de6dad3b0e76004936b1a9f89d5e3db02",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18067",
      "published": "2026-10-13T09:52:02Z",
      "updated": "2026-10-13T09:52:02Z",
      "revision": 1,
      "metadata_sha256": "d2a91ec0f7caecdc29fc8a2a6b8c150ed552eb6042e89860ffe7e7cd1f6096f6",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18054",
      "published": "2026-10-13T09:43:23Z",
      "updated": "2026-10-14T09:11:34Z",
      "revision": 2,
      "metadata_sha256": "c3faebd8a94123fe083c45a7160e901bd57b7b7e2f8f32feede58e9ce7831ae3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18019",
      "published": "2026-10-13T09:14:58Z",
      "updated": "2026-10-13T09:14:58Z",
      "revision": 1,
      "metadata_sha256": "67789a42649160df5a74ccb424203798d0e7de35f74ec2a3e790698da84b7450",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18011",
      "published": "2026-10-13T09:10:58Z",
      "updated": "2026-10-13T09:10:58Z",
      "revision": 1,
      "metadata_sha256": "9ddfac95e2ff03c7dc1b36a25b030c61cddbcbd9a1bbc1725235eae78f27c8b9",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18010",
      "published": "2026-10-13T09:06:28Z",
      "updated": "2026-10-14T09:28:32Z",
      "revision": 2,
      "metadata_sha256": "f5d190af92894fa4ed261b98341529ca4a1942e02e00c50434ea64cce5bf5bb0",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17994",
      "published": "2026-10-13T08:57:21Z",
      "updated": "2026-10-13T08:57:21Z",
      "revision": 1,
      "metadata_sha256": "985817ab32568531c7d0e41985423099da53a14ba756f93eb304aafe9f24868d",
      "repository_status": "new",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.17953",
      "published": "2026-10-13T08:36:20Z",
      "updated": "2026-10-13T08:36:20Z",
      "revision": 1,
      "metadata_sha256": "5d58f70b5bfff348387253ca869f3b53457362aaaf778ab79d0fa94ce3b87741",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.17900",
      "published": "2026-10-13T07:55:23Z",
      "updated": "2026-10-13T07:55:23Z",
      "revision": 1,
      "metadata_sha256": "8640382c206332e9f7f9f756794900f86cf233bb47144e4768aaf9a2bdbf5754",
      "repository_status": "new",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.17895",
      "published": "2026-10-13T07:49:50Z",
      "updated": "2026-10-14T06:37:47Z",
      "revision": 2,
      "metadata_sha256": "abb31988f03961db2204da8575b73e7d47026b1a7adcc7d4d7c2bd35b90c86f8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.17893",
      "published": "2026-10-13T07:46:48Z",
      "updated": "2026-10-13T07:46:48Z",
      "revision": 1,
      "metadata_sha256": "fdff8f581ca7a4ffe4b99218ae0862e62a6ea570914ee251ff7f84c091579a69",
      "repository_status": "new",
      "matched_queries": [
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17867",
      "published": "2026-10-13T07:27:44Z",
      "updated": "2026-10-14T04:27:19Z",
      "revision": 2,
      "metadata_sha256": "78f9408a89bc6eb0978332e0d17bef4c7eaab296392c444cbafcab192967390b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.17856",
      "published": "2026-10-13T07:20:58Z",
      "updated": "2026-10-14T05:39:34Z",
      "revision": 2,
      "metadata_sha256": "c3bc5555a8bf31c7aa11eaee6bfb6abda9b95ed88dc3646dfceef85f780f9d79",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.17824",
      "published": "2026-10-13T06:44:33Z",
      "updated": "2026-10-13T06:44:33Z",
      "revision": 1,
      "metadata_sha256": "0ea01feea99b5d24e08ae2ce13cd294c00817a7720c98cd80368491d7bf20ecd",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.17804",
      "published": "2026-10-13T06:30:52Z",
      "updated": "2026-10-13T06:30:52Z",
      "revision": 1,
      "metadata_sha256": "d59b2202713f9747a6491b3bc0f37940e25a08aa0445e32c04f5a86b67478233",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.17771",
      "published": "2026-10-13T05:57:20Z",
      "updated": "2026-10-13T05:57:20Z",
      "revision": 1,
      "metadata_sha256": "8eb4dcaa31f4a5e2679c93625588bec7c5db377085e690496daff5f47ac4a601",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.17767",
      "published": "2026-10-13T05:53:34Z",
      "updated": "2026-10-13T05:53:34Z",
      "revision": 1,
      "metadata_sha256": "d23abe934601094635614380115eb197f2dea1e4dca2bdf06b4b1dbfad5d00ed",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17734",
      "published": "2026-10-13T05:13:10Z",
      "updated": "2026-10-13T05:13:10Z",
      "revision": 1,
      "metadata_sha256": "aa86462e1075b27ef0388ada10fdca23994b8477e47ae99fd979b70f9c8d5218",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.17733",
      "published": "2026-10-13T05:13:04Z",
      "updated": "2026-10-13T05:13:04Z",
      "revision": 1,
      "metadata_sha256": "0d5c91d9f9a6d49696ba3a0ae7b1b75507523012918087d2defb3ab4a5da5f48",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17726",
      "published": "2026-10-13T05:02:58Z",
      "updated": "2026-10-13T05:02:58Z",
      "revision": 1,
      "metadata_sha256": "2347ec084af61f410d018381204982b71e5ed854f2020c43d0ea4892edd2d89f",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.17666",
      "published": "2026-10-13T03:49:32Z",
      "updated": "2026-10-13T03:49:32Z",
      "revision": 1,
      "metadata_sha256": "452cfa65515251906e317915945e30fd4861f5e00487c50adf6dd929c3857608",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.17654",
      "published": "2026-10-13T03:32:37Z",
      "updated": "2026-10-13T03:32:37Z",
      "revision": 1,
      "metadata_sha256": "5a7e5e2d7db2b4e1a959250b1b215906d63dcb917643e054c00ad5197de51600",
      "repository_status": "new",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.17623",
      "published": "2026-10-13T02:45:54Z",
      "updated": "2026-10-14T05:22:37Z",
      "revision": 2,
      "metadata_sha256": "7683527bf59a696de6a00c82d2f037d1a72e6f156ee2c708e1b3f3e1e86535f5",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.17616",
      "published": "2026-10-13T02:39:03Z",
      "updated": "2026-10-13T02:39:03Z",
      "revision": 1,
      "metadata_sha256": "417c302cb662362d1f109b1e43ddbce327b9d16397c4138d97cd6f38fee43c48",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17531",
      "published": "2026-10-13T00:52:32Z",
      "updated": "2026-10-13T00:52:32Z",
      "revision": 1,
      "metadata_sha256": "b6c9b45391f6b618885efe53e0e4d6c58ec0c3dcfe98331bb7565b6735df580a",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.18924",
      "published": "2026-10-12T23:01:01Z",
      "updated": "2026-10-12T23:01:01Z",
      "revision": 1,
      "metadata_sha256": "d591968a9ebd7a3a12f3469fc21fd3a4a9c3dc31714e975fde877ec6cf89d229",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.17471",
      "published": "2026-10-12T22:35:08Z",
      "updated": "2026-10-12T22:35:08Z",
      "revision": 1,
      "metadata_sha256": "b0dd11ba530f42812abd4bd4f380c52ee20f6d09f6966aa9d6c5ffde42d01f73",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17456",
      "published": "2026-10-12T22:16:45Z",
      "updated": "2026-10-12T22:16:45Z",
      "revision": 1,
      "metadata_sha256": "1e133df9539370dd4d0ebd2cbfd24aa75b6f028d36153784fde0d4423c5479a9",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17444",
      "published": "2026-10-12T22:04:36Z",
      "updated": "2026-10-12T22:04:36Z",
      "revision": 1,
      "metadata_sha256": "80a9be9ae288a3eb51a022fe1511a10ee1b96b9356d9e3a219ccdaa399bd95ec",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.17426",
      "published": "2026-10-12T21:39:21Z",
      "updated": "2026-10-12T21:39:21Z",
      "revision": 1,
      "metadata_sha256": "5797bff4780dead79bedf824b614adde5bdb8da533333c4c621bc71eb4cc4638",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "process-reward",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.17409",
      "published": "2026-10-12T21:17:48Z",
      "updated": "2026-10-12T21:17:48Z",
      "revision": 1,
      "metadata_sha256": "f21e32f646b930469e19c434e1e4f33e057f267906f58bd00c43835f89a54702",
      "repository_status": "new",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.17407",
      "published": "2026-10-12T21:13:37Z",
      "updated": "2026-10-14T17:05:28Z",
      "revision": 2,
      "metadata_sha256": "10bfe02c3630deff913d05a15e2a91dc6561fff8a7052bfcfd4a8d87cde454c8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.17397",
      "published": "2026-10-12T21:02:26Z",
      "updated": "2026-10-12T21:02:26Z",
      "revision": 1,
      "metadata_sha256": "3f41d927d87e59b28d1240d7237501e67e640aefdab393ac3b9539cf4d07af49",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation",
        "policy-llm-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.17370",
      "published": "2026-10-12T20:27:32Z",
      "updated": "2026-10-12T20:27:32Z",
      "revision": 1,
      "metadata_sha256": "e8e37e725ea1d0267bdf5d8a41284737f194f2153d66e5d1a91e3280d36da0e7",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17309",
      "published": "2026-10-12T19:05:56Z",
      "updated": "2026-10-12T19:05:56Z",
      "revision": 1,
      "metadata_sha256": "fc06eef76558b0226e4c4400878917b02960062fb142ba25a0fcde6589b43532",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17306",
      "published": "2026-10-12T18:59:35Z",
      "updated": "2026-10-12T18:59:35Z",
      "revision": 1,
      "metadata_sha256": "455fc1fca7edb9f4f95eca0f229e7e59dbf9ec2a7e6cf58feb6de74255f3b383",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.17246",
      "published": "2026-10-12T18:11:58Z",
      "updated": "2026-10-12T18:11:58Z",
      "revision": 1,
      "metadata_sha256": "b28f27314a0f1c2e11a35e948253c8a65ca970c2377046a8292a758f558cf84c",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17214",
      "published": "2026-10-12T18:00:01Z",
      "updated": "2026-10-12T18:00:01Z",
      "revision": 1,
      "metadata_sha256": "823f274891d5d281c6975a96efca6dd7f434f8e7c32a782ec75fb45847b75ac9",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17174",
      "published": "2026-10-12T17:46:33Z",
      "updated": "2026-10-12T17:46:33Z",
      "revision": 1,
      "metadata_sha256": "027996de8a00a38f29d030604c204f61374f2a01ed80c0f2fe2de459923556f5",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17125",
      "published": "2026-10-12T17:15:43Z",
      "updated": "2026-10-12T17:15:43Z",
      "revision": 1,
      "metadata_sha256": "725f1a9cbf61fc942d7030b6cbe0c846fb5cb7172ad8e73cc2df55000a798f09",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.17113",
      "published": "2026-10-12T17:05:20Z",
      "updated": "2026-10-12T17:05:20Z",
      "revision": 1,
      "metadata_sha256": "7050b259ffc2e9cf663c963b832a7846ee2c3a9b9917b7cadf4d785cbef08f46",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.17042",
      "published": "2026-10-12T16:15:07Z",
      "updated": "2026-10-12T16:15:07Z",
      "revision": 1,
      "metadata_sha256": "644fb4b0cfb44791f836a9da1af7e96f5bbbb41ba90f28a0a48167cf99afdb4a",
      "repository_status": "new",
      "matched_queries": [
        "post-training",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.18917",
      "published": "2026-10-12T15:48:03Z",
      "updated": "2026-10-12T15:48:03Z",
      "revision": 1,
      "metadata_sha256": "808551fd3994c0e85df56515fe14b91a7b43850ff334d95f1d7f6ad2d0cffb55",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.16948",
      "published": "2026-10-12T15:20:24Z",
      "updated": "2026-10-14T09:30:39Z",
      "revision": 2,
      "metadata_sha256": "bee6b1d4df71536357c0a24599b6788d795d236529c9bee2756d09947c159010",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.16866",
      "published": "2026-10-12T14:33:16Z",
      "updated": "2026-10-12T14:33:16Z",
      "revision": 1,
      "metadata_sha256": "cd430fca40babae176e1cf6d1c2dfe61f2b59cd484c19cce9819f7b448cb2413",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.16867",
      "published": "2026-10-12T14:33:16Z",
      "updated": "2026-10-12T14:33:16Z",
      "revision": 1,
      "metadata_sha256": "eeb02509fcc332494c83e5005f7c7cab43bd03252b3da00a7da7da46b23239e0",
      "repository_status": "new",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.16794",
      "published": "2026-10-12T13:47:36Z",
      "updated": "2026-10-12T13:47:36Z",
      "revision": 1,
      "metadata_sha256": "9240f9d8d1fd9f431828394eb45253b4c2ed0a9bd24ccdc549cde94ec36aa1ea",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.16597",
      "published": "2026-10-12T11:18:24Z",
      "updated": "2026-10-14T06:48:06Z",
      "revision": 2,
      "metadata_sha256": "6c4fd651210242d80c93f2a04e722036402703ce2efc079e575182cf593657f9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.16596",
      "published": "2026-10-12T11:18:18Z",
      "updated": "2026-10-14T10:13:15Z",
      "revision": 2,
      "metadata_sha256": "b67c07b2a588531d073cb760b0dd3fc52f5f1db8e07b5384062c66d07111e731",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.16592",
      "published": "2026-10-12T11:16:14Z",
      "updated": "2026-10-12T11:16:14Z",
      "revision": 1,
      "metadata_sha256": "f0c739f8e1932938e22f1047c613fd236600a720d9983a1e8d3a22eac2896a5b",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.16533",
      "published": "2026-10-12T10:21:21Z",
      "updated": "2026-10-12T10:21:21Z",
      "revision": 1,
      "metadata_sha256": "86bb9f033fa1252f3a367fb889b72b4c9e74ab96ba9cbe4896dba923ad8b21a9",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "process-reward",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.16523",
      "published": "2026-10-12T10:11:38Z",
      "updated": "2026-10-12T10:11:38Z",
      "revision": 1,
      "metadata_sha256": "26aecb8a314655765da990d49c41cd3c02dbf0ba4de1007e67476cf01949d87a",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.16517",
      "published": "2026-10-12T10:08:28Z",
      "updated": "2026-10-12T10:08:28Z",
      "revision": 1,
      "metadata_sha256": "ed442f5a14725135a8c4b20edb0c2d8f2a96ea03844326e61cfc76ab94fb7c9d",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.16489",
      "published": "2026-10-12T09:43:00Z",
      "updated": "2026-10-12T09:43:00Z",
      "revision": 1,
      "metadata_sha256": "a3bf17f3776da8950ccf8662574e7a23650b236ee44fad2080f1879d6cfe4a71",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.16368",
      "published": "2026-10-12T08:20:04Z",
      "updated": "2026-10-12T08:20:04Z",
      "revision": 1,
      "metadata_sha256": "2399473d4fc47093a0a1389e303fcae337ce3a78ed7a7900336b362b05fee6a5",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.16354",
      "published": "2026-10-12T08:11:35Z",
      "updated": "2026-10-12T08:11:35Z",
      "revision": 1,
      "metadata_sha256": "cf90b714a8a67f74b1a78505033d9dc9cf5d7a03360b28403fb8ce991f4a46dc",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.16352",
      "published": "2026-10-12T08:08:16Z",
      "updated": "2026-10-12T08:08:16Z",
      "revision": 1,
      "metadata_sha256": "d78b3d93a3c3ceca559419e532a284e0953b6ae6b262163c76b3839cae10b10d",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "policy-llm-abbreviation",
        "post-training",
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.16318",
      "published": "2026-10-12T07:41:53Z",
      "updated": "2026-10-12T07:41:53Z",
      "revision": 1,
      "metadata_sha256": "edc63284a02e814039534e12c95aa67f6a78591db71a64201f220816eb04ebfa",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.16226",
      "published": "2026-10-12T06:03:33Z",
      "updated": "2026-10-12T06:03:33Z",
      "revision": 1,
      "metadata_sha256": "b35c486d991ca60ca6104f2fc14a2934926c6d835f27f8c7d8b37ebae22f8bae",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.16172",
      "published": "2026-10-12T04:46:04Z",
      "updated": "2026-10-12T04:46:04Z",
      "revision": 1,
      "metadata_sha256": "9a9862f0a07aff4a53f1c669e29a36fda605ba2c9c8c10aac3f2df3e68e42c30",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.16105",
      "published": "2026-10-12T03:13:09Z",
      "updated": "2026-10-12T03:13:09Z",
      "revision": 1,
      "metadata_sha256": "7fd2e4db337928acc1da59b02a7c0f152b9e19478bd3b270f3b605a6ffa69d78",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.16104",
      "published": "2026-10-12T03:12:53Z",
      "updated": "2026-10-12T03:12:53Z",
      "revision": 1,
      "metadata_sha256": "508f81875599cdb0e4147a4e6a1823c5d0f8138c4fc5b9a89544a6113261b578",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.16043",
      "published": "2026-10-12T01:36:17Z",
      "updated": "2026-10-12T01:36:17Z",
      "revision": 1,
      "metadata_sha256": "a48f7016797e21abc28b5608bd14bb9eb704c2d8d722828bec261e19ded80ad9",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.15924",
      "published": "2026-10-11T21:10:19Z",
      "updated": "2026-10-11T21:10:19Z",
      "revision": 1,
      "metadata_sha256": "0069d1913f6a3be42a11efc256ca8cc16695d5f1080d259f67359b2c0c2f19e3",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.15899",
      "published": "2026-10-11T20:27:58Z",
      "updated": "2026-10-11T20:27:58Z",
      "revision": 1,
      "metadata_sha256": "ad478f3e34654c4cdfcdea94bb60afad52b9b47511b19b10a20cbbc41481104f",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15894",
      "published": "2026-10-11T20:19:05Z",
      "updated": "2026-10-11T20:19:05Z",
      "revision": 1,
      "metadata_sha256": "b76dfecb0e1a29860df75c4826be27662b81bb06dd92914664e9f3a5b10afbf7",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15888",
      "published": "2026-10-11T20:09:24Z",
      "updated": "2026-10-11T20:09:24Z",
      "revision": 1,
      "metadata_sha256": "36d77a336bace1243eb6c0aa21f1167b42b9688ec73afb6f2869c70bc11d876f",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18904",
      "published": "2026-10-11T19:40:57Z",
      "updated": "2026-10-11T19:40:57Z",
      "revision": 1,
      "metadata_sha256": "4714f8e57ac3a0e49cab170c94ac3f4c54b73de230be9676414d40de082078bb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.15864",
      "published": "2026-10-11T19:33:28Z",
      "updated": "2026-10-11T19:33:28Z",
      "revision": 1,
      "metadata_sha256": "46746976f3820691eb44c338cb67ab327fcdbedb2c29f16e0ae39828c4222f26",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.15840",
      "published": "2026-10-11T18:46:50Z",
      "updated": "2026-10-11T18:46:50Z",
      "revision": 1,
      "metadata_sha256": "1a504aefd6bff73ccab6f190437f9c2a1ad66628586a42e7c045a71285a3ca08",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15810",
      "published": "2026-10-11T17:57:17Z",
      "updated": "2026-10-11T17:57:17Z",
      "revision": 1,
      "metadata_sha256": "5ded7658e0297b133f1673023b0dddfa38658651e14be553279a7b9ff449b103",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.15778",
      "published": "2026-10-11T17:05:39Z",
      "updated": "2026-10-14T09:42:42Z",
      "revision": 2,
      "metadata_sha256": "ea41c1fdcdc344d264eb1749936ceabf925ee0ef3101ca7ff0966f0257127b7f",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15772",
      "published": "2026-10-11T16:54:58Z",
      "updated": "2026-10-11T16:54:58Z",
      "revision": 1,
      "metadata_sha256": "cff59fb06723a1a637e3cb546ff8df062bdabc79e2c7250a4a9246499d63ef9c",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "process-reward",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15715",
      "published": "2026-10-11T15:58:04Z",
      "updated": "2026-10-11T15:58:04Z",
      "revision": 1,
      "metadata_sha256": "2b39139ba2676bde35cc07f1ddb5b28b5562aee0306854272804a796d4178d20",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.15669",
      "published": "2026-10-11T14:47:50Z",
      "updated": "2026-10-14T16:16:48Z",
      "revision": 2,
      "metadata_sha256": "2fd7b17df6a751f979d10284f93fb77ffc47c99d30ab0c7932989ec31be33e59",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.15578",
      "published": "2026-10-11T12:44:36Z",
      "updated": "2026-10-11T12:44:36Z",
      "revision": 1,
      "metadata_sha256": "d1c74b17d70fc600f6a69c9422337fb573737b65a5e31fa6f9374404713c3b1b",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.15556",
      "published": "2026-10-11T11:59:18Z",
      "updated": "2026-10-11T11:59:18Z",
      "revision": 1,
      "metadata_sha256": "ce1ebfa94007e3468e4fb606a6a51c8000d2e5fdaec7d6c8812ace5a8e6c0bcc",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15542",
      "published": "2026-10-11T11:34:43Z",
      "updated": "2026-10-11T11:34:43Z",
      "revision": 1,
      "metadata_sha256": "384517bee433d46c06d451e38ec02c27c8088b4017f95937c558a7cefe97f7ce",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.15514",
      "published": "2026-10-11T10:27:26Z",
      "updated": "2026-10-11T10:27:26Z",
      "revision": 1,
      "metadata_sha256": "c99e2b1ae03273663467ffc121365c57b0699fb45e39994a4c0c296e9ed7e77a",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.15449",
      "published": "2026-10-11T08:50:07Z",
      "updated": "2026-10-14T11:58:17Z",
      "revision": 2,
      "metadata_sha256": "ca213d0356afa20a8ef0f033641d2fc41394f7abce64064e4c632d8de06dc3d2",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.15398",
      "published": "2026-10-11T06:53:27Z",
      "updated": "2026-10-11T06:53:27Z",
      "revision": 1,
      "metadata_sha256": "77fabbb3f10b6d4dcc21edb4fcbc5b3a0a25aa20c4dc6372a4c092789f808d58",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15371",
      "published": "2026-10-11T05:52:29Z",
      "updated": "2026-10-11T05:52:29Z",
      "revision": 1,
      "metadata_sha256": "45a9bb0832bd90c6ee41ff7edf3f61264460e6969914d0a32c1e581daa971761",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.15368",
      "published": "2026-10-11T05:46:07Z",
      "updated": "2026-10-11T05:46:07Z",
      "revision": 1,
      "metadata_sha256": "fb221894dc1e1423288528eb74c027b91c3db0a2f8b8b83f8db8450bbc4c1c50",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.15328",
      "published": "2026-10-11T04:07:53Z",
      "updated": "2026-10-11T04:07:53Z",
      "revision": 1,
      "metadata_sha256": "07762e4e2fc836cc4d2785652a795686942b5d52a8187c1d07ffef96ef826f6a",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15322",
      "published": "2026-10-11T03:51:47Z",
      "updated": "2026-10-14T07:18:02Z",
      "revision": 2,
      "metadata_sha256": "e51b3754171daa30416394dd2367d76e7149b03de9a68e4a6e69fd6f4059d820",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.15277",
      "published": "2026-10-11T02:16:29Z",
      "updated": "2026-10-11T02:16:29Z",
      "revision": 1,
      "metadata_sha256": "5f8a5f120f16713e974ee39e07be16e7d6d6d356405d9fb45097501db7b6b02d",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15258",
      "published": "2026-10-11T01:10:19Z",
      "updated": "2026-10-11T01:10:19Z",
      "revision": 1,
      "metadata_sha256": "0bc72ed0e4ba571b91fb0887a8c2add9de7a62ee5fc46bdadf6d42e1359ae955",
      "repository_status": "new",
      "matched_queries": [
        "post-training",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.15244",
      "published": "2026-10-11T00:33:53Z",
      "updated": "2026-10-11T00:33:53Z",
      "revision": 1,
      "metadata_sha256": "6bcca235511c3800d7fbe18f23458ca7fb0a98d90bb18bf034c73fe81364700d",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.15173",
      "published": "2026-10-10T20:51:19Z",
      "updated": "2026-10-10T20:51:19Z",
      "revision": 1,
      "metadata_sha256": "b420a0cef7932bf3eb36c99ccec941f81350571745b94aac33642040619be145",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15154",
      "published": "2026-10-10T20:10:59Z",
      "updated": "2026-10-10T20:10:59Z",
      "revision": 1,
      "metadata_sha256": "dcf0a3b6d7e07efc7efb039bb8c15860c9ad0786c90c3c9bf3ec9dd3d0886a90",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15097",
      "published": "2026-10-10T18:14:59Z",
      "updated": "2026-10-10T18:14:59Z",
      "revision": 1,
      "metadata_sha256": "83537a9f0b67c5e1f6fabc56f0191e879a6d0ce20d847daf52651b2793e93e93",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.15058",
      "published": "2026-10-10T16:49:38Z",
      "updated": "2026-10-10T16:49:38Z",
      "revision": 1,
      "metadata_sha256": "37568ece999c12eca67d48c207d73f09c951111f5fbc76557a6be15c54d9da90",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15056",
      "published": "2026-10-10T16:48:27Z",
      "updated": "2026-10-10T16:48:27Z",
      "revision": 1,
      "metadata_sha256": "c6047dc42b3cf0261b42c84dcf804d55f9a930ce6225d27a59c407033843d0cf",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.15044",
      "published": "2026-10-10T16:30:22Z",
      "updated": "2026-10-10T16:30:22Z",
      "revision": 1,
      "metadata_sha256": "7ee013dbc8bbcfabcb41525369338614a625fb84d581d0cfafe9c4bbb0dc07b8",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.15033",
      "published": "2026-10-10T16:18:41Z",
      "updated": "2026-10-10T16:18:41Z",
      "revision": 1,
      "metadata_sha256": "f0fd60ef2af2a9aaa5d88d48a2ed102b33b43193d2104b96cd22c0318cfeb567",
      "repository_status": "new",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.14976",
      "published": "2026-10-10T14:47:47Z",
      "updated": "2026-10-10T14:47:47Z",
      "revision": 1,
      "metadata_sha256": "11b0f932e49c9f38171c39d9b84ed13a7981598830c9c67b571a7a1660ad5d7e",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "process-reward",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14959",
      "published": "2026-10-10T14:32:10Z",
      "updated": "2026-10-14T12:33:55Z",
      "revision": 2,
      "metadata_sha256": "0830514fa767f795bcf711cae171d3d5241ad9d81f97295da2a621380a98c109",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.14937",
      "published": "2026-10-10T14:10:07Z",
      "updated": "2026-10-10T14:10:07Z",
      "revision": 1,
      "metadata_sha256": "b464859b2435b167a94737d4cbf779aba8fd532c9b7d9cc8eb48b17268397d07",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14936",
      "published": "2026-10-10T14:09:24Z",
      "updated": "2026-10-10T14:09:24Z",
      "revision": 1,
      "metadata_sha256": "3115169c8f01e96900f3d1b327c49f285192f4d1054a4ca8184bfd14fd3fb2f2",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14913",
      "published": "2026-10-10T13:35:02Z",
      "updated": "2026-10-10T13:35:02Z",
      "revision": 1,
      "metadata_sha256": "fbf4291ca50eff0247fcf74062e6cb1c603954c9e0a8cf5e1155c805a7a03fcb",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.14883",
      "published": "2026-10-10T12:57:40Z",
      "updated": "2026-10-10T12:57:40Z",
      "revision": 1,
      "metadata_sha256": "580f1ef530954896a630d1bf32cbf61c4220040a801dffa3444b6010137dae7b",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14860",
      "published": "2026-10-10T12:30:31Z",
      "updated": "2026-10-10T12:30:31Z",
      "revision": 1,
      "metadata_sha256": "c230d28f812e3b905dd14267842639b546485f24a7eb672093808649747d698b",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.14763",
      "published": "2026-10-10T09:37:30Z",
      "updated": "2026-10-10T09:37:30Z",
      "revision": 1,
      "metadata_sha256": "b3941f7b81410ab076df8625d0dc2536f22342c314f3724d6c655089a049745d",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.14709",
      "published": "2026-10-10T08:28:00Z",
      "updated": "2026-10-10T08:28:00Z",
      "revision": 1,
      "metadata_sha256": "72289f5f3e3ce866be2413053811efa7c60cbcf227a2d79e40764b08d0650d36",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.14705",
      "published": "2026-10-10T08:22:12Z",
      "updated": "2026-10-10T08:22:12Z",
      "revision": 1,
      "metadata_sha256": "9ee1274e577cb3dd98335c590c5d705c01becc8562b4ed5ec4c4f6e30bb33644",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.14612",
      "published": "2026-10-10T05:55:09Z",
      "updated": "2026-10-10T05:55:09Z",
      "revision": 1,
      "metadata_sha256": "3c96735d0eec2594c0f047b1e01dd39a1f820ce3394d7ebf1f2a6e1786d84a3d",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14578",
      "published": "2026-10-10T04:55:56Z",
      "updated": "2026-10-10T04:55:56Z",
      "revision": 1,
      "metadata_sha256": "15d79268950abe0c4dcb729bfab3d902b20b0a1320e75df3d5ce726a9ac19e59",
      "repository_status": "new",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.14572",
      "published": "2026-10-10T04:43:04Z",
      "updated": "2026-10-10T04:43:04Z",
      "revision": 1,
      "metadata_sha256": "8f32d3d739ce86e65df9c552011fbcce14c8ef5c0277517ebb84145852fea4c3",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training",
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.14571",
      "published": "2026-10-10T04:38:49Z",
      "updated": "2026-10-10T04:38:49Z",
      "revision": 1,
      "metadata_sha256": "1fd75cfdab3910be99b1f303737f94c14cfd2fbd467da49ea59fefd4f9d952f2",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14567",
      "published": "2026-10-10T04:38:25Z",
      "updated": "2026-10-14T12:15:23Z",
      "revision": 2,
      "metadata_sha256": "30730bc687431e0e94d301705694c638474ea40eb5d3ab49c6d53b9ad858f677",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.14519",
      "published": "2026-10-10T03:30:09Z",
      "updated": "2026-10-10T03:30:09Z",
      "revision": 1,
      "metadata_sha256": "d22234d7fa8fb9bbd7657eb49b5a597e49705ee1efa324e80493874dcbbb85e2",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14479",
      "published": "2026-10-10T02:22:51Z",
      "updated": "2026-10-10T02:22:51Z",
      "revision": 1,
      "metadata_sha256": "8cecf9aa057e083bb09c74e83d5695e572a5e44c1e6454cd68b4106dcaf01537",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.14474",
      "published": "2026-10-10T02:06:48Z",
      "updated": "2026-10-10T02:06:48Z",
      "revision": 1,
      "metadata_sha256": "dce8a47ff933408ab5150abfcc3ae4de1185001112df7f4c5e2539acec3dcfc3",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14460",
      "published": "2026-10-10T01:38:03Z",
      "updated": "2026-10-10T01:38:03Z",
      "revision": 1,
      "metadata_sha256": "82151053e93dab0d948eb831397825d200bbc352f79a7a0160aeb94e0ce89018",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.14448",
      "published": "2026-10-10T01:24:03Z",
      "updated": "2026-10-10T01:24:03Z",
      "revision": 1,
      "metadata_sha256": "95fe6bcb88a312ff20547af1fc728549680ccdde12a264a6a025961d6d34eb61",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14440",
      "published": "2026-10-10T01:15:04Z",
      "updated": "2026-10-10T01:15:04Z",
      "revision": 1,
      "metadata_sha256": "5a8285654722c9a03b17872d341e3c0e2f1585b4a78648fe84c097b5eddc3dac",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.14405",
      "published": "2026-10-09T23:58:44Z",
      "updated": "2026-10-09T23:58:44Z",
      "revision": 1,
      "metadata_sha256": "25811d8d500519850bfe527a2f1be5c10f620f06406f948460c4ad80f5212ff3",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14400",
      "published": "2026-10-09T23:42:51Z",
      "updated": "2026-10-09T23:42:51Z",
      "revision": 1,
      "metadata_sha256": "a637c4b43e98e82f33502485e63f860d547440c07c6eaeebd6c997f09d2c648e",
      "repository_status": "new",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.14393",
      "published": "2026-10-09T23:32:35Z",
      "updated": "2026-10-09T23:32:35Z",
      "revision": 1,
      "metadata_sha256": "acda66cb23b085feda72412485437c4f1975c5793a971f69915decbb6973ff38",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14350",
      "published": "2026-10-09T21:55:41Z",
      "updated": "2026-10-14T13:20:51Z",
      "revision": 2,
      "metadata_sha256": "b65ffb69be0b4dc398a60d5434fa5419f434da17908f4448671f1cccd22c1496",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.14346",
      "published": "2026-10-09T21:45:51Z",
      "updated": "2026-10-14T16:00:21Z",
      "revision": 2,
      "metadata_sha256": "c36ed56462fe0a356868e2da1237737b5e61036e8c2fb9000f0e99f7e1111598",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14315",
      "published": "2026-10-09T20:53:22Z",
      "updated": "2026-10-14T01:40:37Z",
      "revision": 2,
      "metadata_sha256": "c646fb2c74f852be3e1bf86b270d6cb000590850610e4c7f6654d883486ae85e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.14309",
      "published": "2026-10-09T20:36:45Z",
      "updated": "2026-10-09T20:36:45Z",
      "revision": 1,
      "metadata_sha256": "0d8bb76b833ae6c4426dfcd9ba1c0d73cd515d84d6cc4b2cd8ccdc6173835ce2",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14270",
      "published": "2026-10-09T19:43:51Z",
      "updated": "2026-10-09T19:43:51Z",
      "revision": 1,
      "metadata_sha256": "4067794d60a28d532a4131b736188952c73e414c4bb73b1202b30cfad8231bb5",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14238",
      "published": "2026-10-09T18:56:21Z",
      "updated": "2026-10-09T18:56:21Z",
      "revision": 1,
      "metadata_sha256": "2eb8f128e17d640d46b964dac8e9413790c680d84c1bfcdfcde4f101b2295a62",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.14180",
      "published": "2026-10-09T18:00:33Z",
      "updated": "2026-10-09T18:00:33Z",
      "revision": 1,
      "metadata_sha256": "6f5c0dfb1a5b01c0b217a48411f7d35a65831b1766336a9b9ed0e159ff92d00e",
      "repository_status": "new",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.13935",
      "published": "2026-10-09T17:56:59Z",
      "updated": "2026-10-14T03:57:52Z",
      "revision": 3,
      "metadata_sha256": "390ada5e44f100c4a50fc6f007aef8a2658e1db23e81ccdc9e3614b33a18cb50",
      "repository_status": "reviewed",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.13928",
      "published": "2026-10-09T17:55:06Z",
      "updated": "2026-10-14T17:58:11Z",
      "revision": 2,
      "metadata_sha256": "0accc459c4f1c1c4d3bbd86dc912215ff1c515eab64747b19e9ec68ef986876d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.13923",
      "published": "2026-10-09T17:53:46Z",
      "updated": "2026-10-09T17:53:46Z",
      "revision": 1,
      "metadata_sha256": "23a0a6e2d8d9f0ff2eda315ab929dabf130a15171597b763eaabbe0347474747",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14163",
      "published": "2026-10-09T17:51:50Z",
      "updated": "2026-10-09T17:51:50Z",
      "revision": 1,
      "metadata_sha256": "ab4561db9676712e2789242e69d7f2e80730ad532f1c9dbd442623d0bebd4ecc",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.13896",
      "published": "2026-10-09T17:42:14Z",
      "updated": "2026-10-09T17:42:14Z",
      "revision": 1,
      "metadata_sha256": "29834deab7149396e2434ba14013ce57637fcbb0348d0bff600c5ccacd173614",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.13821",
      "published": "2026-10-09T16:33:27Z",
      "updated": "2026-10-09T16:33:27Z",
      "revision": 1,
      "metadata_sha256": "421b9af483b0d8c0b4ed49b697ec7b2e388fec2ca47ad2bac8c983daaf6f46d6",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.13755",
      "published": "2026-10-09T15:41:37Z",
      "updated": "2026-10-09T15:41:37Z",
      "revision": 1,
      "metadata_sha256": "0980b474ee624d95184e3b1b8960fd4a6007b7b0228dc790f95f34d30aa121e8",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.13744",
      "published": "2026-10-09T15:36:47Z",
      "updated": "2026-10-09T15:36:47Z",
      "revision": 1,
      "metadata_sha256": "422b919614c5d1fecd0478ea66045adc1b3ea1dea073a32bd19140aba7198eca",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13672",
      "published": "2026-10-09T14:37:51Z",
      "updated": "2026-10-09T14:37:51Z",
      "revision": 1,
      "metadata_sha256": "dcf85e2fe1172dd34f7655958ccd0639f8344dd65bd6253908f6fd57351c0c2e",
      "repository_status": "implemented",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13653",
      "published": "2026-10-09T14:29:28Z",
      "updated": "2026-10-09T14:29:28Z",
      "revision": 1,
      "metadata_sha256": "aa2385d65261236c9211ab03345f4d1a5334530b2f637a92d6de38191c909601",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.13617",
      "published": "2026-10-09T14:00:36Z",
      "updated": "2026-10-09T14:00:36Z",
      "revision": 1,
      "metadata_sha256": "e0befb82841f67a5b9a2297f0e68e9e06579a60e7813bdb18d56f54f404fbcf7",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.13504",
      "published": "2026-10-09T12:30:14Z",
      "updated": "2026-10-09T12:30:14Z",
      "revision": 1,
      "metadata_sha256": "e926908210ee8e99a23b05681f18af2a512cc7a3f2cda4bc97d0bc7bcdcd5e76",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13485",
      "published": "2026-10-09T12:18:49Z",
      "updated": "2026-10-09T12:18:49Z",
      "revision": 1,
      "metadata_sha256": "88154fc26a9bdb38de2b01a55ada188b30bac551e225d64184936d1f542dbf5b",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.13353",
      "published": "2026-10-09T10:28:54Z",
      "updated": "2026-10-09T10:28:54Z",
      "revision": 1,
      "metadata_sha256": "cd6641640ccfc6e886a994f05dd892b8bf022d3c9cf6c3adb05b574ffa1075bc",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13330",
      "published": "2026-10-09T10:07:37Z",
      "updated": "2026-10-09T10:07:37Z",
      "revision": 1,
      "metadata_sha256": "d1ccb9c4b0c64d36add6c01ccb40ff01be64093e3a1c5ca5b5712dbdd23e58f2",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.13306",
      "published": "2026-10-09T09:52:15Z",
      "updated": "2026-10-09T09:52:15Z",
      "revision": 1,
      "metadata_sha256": "9b16db76078e09f6ff38ae8ee20469a8afc4a54657b8560e18d9f66127f564f1",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13272",
      "published": "2026-10-09T09:23:21Z",
      "updated": "2026-10-09T09:23:21Z",
      "revision": 1,
      "metadata_sha256": "b3fdc415319ac0cb84c8dc8a0ddcaca0ab7d5817d0507b00762735df177af9d1",
      "repository_status": "reviewed",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13264",
      "published": "2026-10-09T09:15:34Z",
      "updated": "2026-10-09T09:15:34Z",
      "revision": 1,
      "metadata_sha256": "d091af6fdfe7637628fe8951d37d9dd45b35b355aa83caae6a6ea3ccfda6532e",
      "repository_status": "implemented",
      "matched_queries": [
        "opd-abbreviation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13257",
      "published": "2026-10-09T09:03:37Z",
      "updated": "2026-10-09T09:03:37Z",
      "revision": 1,
      "metadata_sha256": "856f6362ac6ac95c8dcf1a9bedba80f2009fc4598aff0d6b187090f7646e77c4",
      "repository_status": "implemented",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13238",
      "published": "2026-10-09T08:54:07Z",
      "updated": "2026-10-09T08:54:07Z",
      "revision": 1,
      "metadata_sha256": "08d84a0c91e42ca58f6f0475705f4351cab4d28a149cd702344765652180d89f",
      "repository_status": "implemented",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14118",
      "published": "2026-10-09T08:52:34Z",
      "updated": "2026-10-09T08:52:34Z",
      "revision": 1,
      "metadata_sha256": "f513590cbdd50f35571369a4d0b9155ba6726075ed478c4d7b044860ebb87fea",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.13205",
      "published": "2026-10-09T08:24:48Z",
      "updated": "2026-10-09T08:24:48Z",
      "revision": 1,
      "metadata_sha256": "4825ac580a3a30d40bb79ad00ce0f78b7ce3db0373e60b5f10390377444fa0ab",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13202",
      "published": "2026-10-09T08:22:40Z",
      "updated": "2026-10-09T08:22:40Z",
      "revision": 1,
      "metadata_sha256": "b57c54c6a88065173d2c8ccbb687bf0f70095bd053ed18fab339e59f376d12e4",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13082",
      "published": "2026-10-09T06:36:45Z",
      "updated": "2026-10-14T11:58:50Z",
      "revision": 2,
      "metadata_sha256": "51eee35748bb7b46706596347013f526c1a7b424fb8f738579a134d1af8cb72f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.13058",
      "published": "2026-10-09T06:11:39Z",
      "updated": "2026-10-09T06:11:39Z",
      "revision": 1,
      "metadata_sha256": "89dbf0a4be3a948ddffc26deb11f7066bb5f52136b0d0ffcd36e4f57227c66e8",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13045",
      "published": "2026-10-09T06:01:48Z",
      "updated": "2026-10-09T06:01:48Z",
      "revision": 1,
      "metadata_sha256": "30afd0e1ff302ea90251bf1f155c44edcb40c8f8d94567c3a8b82d4f0507d386",
      "repository_status": "reviewed",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13035",
      "published": "2026-10-09T05:46:54Z",
      "updated": "2026-10-09T05:46:54Z",
      "revision": 1,
      "metadata_sha256": "9887e7c6fbf1a911aa0b55bb3065d8bde9f02c35b3fcedd54724e319765b906d",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.13025",
      "published": "2026-10-09T05:28:02Z",
      "updated": "2026-10-09T05:28:02Z",
      "revision": 1,
      "metadata_sha256": "9dcaedd359a8af65e74bf93e0303e1114753ad9066f35c6ffbac35fb11048d46",
      "repository_status": "implemented",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13020",
      "published": "2026-10-09T05:22:07Z",
      "updated": "2026-10-09T05:22:07Z",
      "revision": 1,
      "metadata_sha256": "d863f812e92665240a7aaa38feccd1fde93b15640d3c3ab6eb5770e97fcd3da8",
      "repository_status": "implemented",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13015",
      "published": "2026-10-09T05:17:26Z",
      "updated": "2026-10-09T05:17:26Z",
      "revision": 1,
      "metadata_sha256": "86cf2d18cf573bd8ee820840130f92976f481b90090a59fa4d7b9c8b60a7f922",
      "repository_status": "implemented",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12995",
      "published": "2026-10-09T04:57:55Z",
      "updated": "2026-10-09T04:57:55Z",
      "revision": 1,
      "metadata_sha256": "2c39b356f44d53904f3420b1ba9f59a2b74b98839b09a300d8912ec67c0f09dc",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.12885",
      "published": "2026-10-09T02:20:29Z",
      "updated": "2026-10-09T02:20:29Z",
      "revision": 1,
      "metadata_sha256": "e4d7332eb671bbe1a603a800888bb2e31de11a5e3a7f41feefd331e6759d4d55",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.12848",
      "published": "2026-10-09T01:15:10Z",
      "updated": "2026-10-14T04:10:44Z",
      "revision": 2,
      "metadata_sha256": "9929b40c92e0e5b9e819d289c98d071af3a6b828d7cb3b38480309c354cfa023",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.12828",
      "published": "2026-10-09T00:23:39Z",
      "updated": "2026-10-09T00:23:39Z",
      "revision": 1,
      "metadata_sha256": "475218baf92c7bc74ffdfdab6341ba803b4f96472d4a14a3bc467ee276a70964",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12813",
      "published": "2026-10-08T23:49:50Z",
      "updated": "2026-10-08T23:49:50Z",
      "revision": 1,
      "metadata_sha256": "29751d4a009b02ffd67f583ba59becb2733070242322bd6b1ca4d3ef082062bc",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12757",
      "published": "2026-10-08T22:08:10Z",
      "updated": "2026-10-08T22:08:10Z",
      "revision": 1,
      "metadata_sha256": "fc050b758e1e7b97f72c451539f70179ea7fa1302bfc951e05072e43b1cc3cc9",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12707",
      "published": "2026-10-08T20:38:25Z",
      "updated": "2026-10-08T20:38:25Z",
      "revision": 1,
      "metadata_sha256": "893ea357afc699e9113223773780df0e20f95153c4cb5290505e46cab4347d12",
      "repository_status": "implemented",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18890",
      "published": "2026-10-08T20:34:38Z",
      "updated": "2026-10-08T20:34:38Z",
      "revision": 1,
      "metadata_sha256": "a00d006933c59c142797c07b3c0f522e2d03e982728965cba0d387257b44747f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.12659",
      "published": "2026-10-08T19:25:48Z",
      "updated": "2026-10-08T19:25:48Z",
      "revision": 1,
      "metadata_sha256": "e981101076d0a169c08fbaf5a8198308f7fd8b3dffd43e0f3dbf9b0b5b27493a",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12601",
      "published": "2026-10-08T18:23:23Z",
      "updated": "2026-10-08T18:23:23Z",
      "revision": 1,
      "metadata_sha256": "58196e9e26ce6cacfbee60eac02e17d16401f1cea5ced520eea79cda322b5ced",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.12582",
      "published": "2026-10-08T18:05:42Z",
      "updated": "2026-10-08T18:05:42Z",
      "revision": 1,
      "metadata_sha256": "a136f0d63ad71edab71c842c28fe4ad2615214b2710557f51e6e074b686104fe",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.12572",
      "published": "2026-10-08T18:01:44Z",
      "updated": "2026-10-08T18:01:44Z",
      "revision": 1,
      "metadata_sha256": "e5310c442dbdc5eda161f59f0eab6de819ac49ceedd7f85f386684f648084123",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12566",
      "published": "2026-10-08T18:00:37Z",
      "updated": "2026-10-08T18:00:37Z",
      "revision": 1,
      "metadata_sha256": "29a8da9c45a6863c339e416bde386c2d0385071f18f177abb40f7d215d93bb75",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.12545",
      "published": "2026-10-08T17:59:52Z",
      "updated": "2026-10-08T17:59:52Z",
      "revision": 1,
      "metadata_sha256": "d16bf334714a8f018a569e5f6b886d69c7162a04bea51a974a45493f246ff12b",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.12420",
      "published": "2026-10-08T17:53:02Z",
      "updated": "2026-10-08T17:53:02Z",
      "revision": 1,
      "metadata_sha256": "8c3a51c6220ce062a28949d9d8cbd745d73138f6b426504e20e10b8bafcd50da",
      "repository_status": "reviewed",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.12410",
      "published": "2026-10-08T17:47:26Z",
      "updated": "2026-10-08T17:47:26Z",
      "revision": 1,
      "metadata_sha256": "908486468b390e3d8d282f1528fa3d9820aa4ecfc364ebee1cdd655739fce415",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.12403",
      "published": "2026-10-08T17:44:19Z",
      "updated": "2026-10-08T17:44:19Z",
      "revision": 1,
      "metadata_sha256": "50ae2b0133f9219582e8ec823135d60a09e5c17b36859f58c4f46a9ea832108e",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12393",
      "published": "2026-10-08T17:39:45Z",
      "updated": "2026-10-14T09:20:50Z",
      "revision": 2,
      "metadata_sha256": "2a51752ca8e6b01dc528404ecbdd457a288635bc80233cf3ecfe47e906fe5896",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.12375",
      "published": "2026-10-08T17:32:08Z",
      "updated": "2026-10-08T17:32:08Z",
      "revision": 1,
      "metadata_sha256": "13b27bfff255fcf29270eee139a8969b1cf69ef3127b468f624b765e84443d0e",
      "repository_status": "implemented",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12367",
      "published": "2026-10-08T17:27:53Z",
      "updated": "2026-10-08T17:27:53Z",
      "revision": 1,
      "metadata_sha256": "c46c8f37c2de0116cf7bbf996f5548ade9111d12bfdbea353661929b98486b40",
      "repository_status": "implemented",
      "matched_queries": [
        "on-policy-distillation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12341",
      "published": "2026-10-08T17:15:48Z",
      "updated": "2026-10-08T17:15:48Z",
      "revision": 1,
      "metadata_sha256": "adb7d7e5178b28973adbccc4dc5b3be81b0a04d4edc84f2206bcb70a967c7037",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.12313",
      "published": "2026-10-08T16:59:40Z",
      "updated": "2026-10-08T16:59:40Z",
      "revision": 1,
      "metadata_sha256": "bbfceb305a239f380baece88abc38a6875c05f206903098957b82d5ab312f9dc",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12274",
      "published": "2026-10-08T16:36:39Z",
      "updated": "2026-10-14T16:34:47Z",
      "revision": 3,
      "metadata_sha256": "e9fff75029a27b979c6696b46073b2f4d5e51ea2a879ffbabc1a1a52c6537105",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.12248",
      "published": "2026-10-08T16:24:12Z",
      "updated": "2026-10-08T16:24:12Z",
      "revision": 1,
      "metadata_sha256": "168faf35c73002137a623afe220297da09a7ef64361e85bceb9bfa7ea432aaa8",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.12235",
      "published": "2026-10-08T16:18:54Z",
      "updated": "2026-10-08T16:18:54Z",
      "revision": 1,
      "metadata_sha256": "85aee206af0ec7aa8698ae9a60b6391aacc0b0b98f99f7379666da4034451de4",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.12207",
      "published": "2026-10-08T15:57:45Z",
      "updated": "2026-10-08T15:57:45Z",
      "revision": 1,
      "metadata_sha256": "4dfbe03619b6248a4afa37035d9a700f7eb74de425e9a0c72c574d9492ec9d98",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.12201",
      "published": "2026-10-08T15:56:28Z",
      "updated": "2026-10-08T15:56:28Z",
      "revision": 1,
      "metadata_sha256": "7391f6351c082f36c800f3390c5bbd29199d9532f7950d10ac344b41af979eb1",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.18889",
      "published": "2026-10-08T15:39:46Z",
      "updated": "2026-10-08T15:39:46Z",
      "revision": 1,
      "metadata_sha256": "ae48be26f22549fa5fddeb3224085b9817620edf8f3f42127d4257d036337ce4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.12061",
      "published": "2026-10-08T14:43:09Z",
      "updated": "2026-10-08T14:43:09Z",
      "revision": 1,
      "metadata_sha256": "3e0b79deafe70156d01d22cedf333f3ffeb826f4d7135d1f1554ab496648b32b",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.12002",
      "published": "2026-10-08T14:06:26Z",
      "updated": "2026-10-08T14:06:26Z",
      "revision": 1,
      "metadata_sha256": "833e44ac9ad1b521b95b9ed4b4b1be9ff63189f6f039728e8aa751568241a731",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11959",
      "published": "2026-10-08T13:41:53Z",
      "updated": "2026-10-08T13:41:53Z",
      "revision": 1,
      "metadata_sha256": "b4bffe36c849ac8a18f1d55544ed6ca03b7bb32c60ac3107a9d3e576f2a24107",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.11896",
      "published": "2026-10-08T13:04:03Z",
      "updated": "2026-10-14T12:21:59Z",
      "revision": 2,
      "metadata_sha256": "677b616c4a06adb7772eccdb0dcaef07335acc779b763d3a1e38115d1a20b0c7",
      "repository_status": "reviewed",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.11854",
      "published": "2026-10-08T12:38:17Z",
      "updated": "2026-10-08T12:38:17Z",
      "revision": 1,
      "metadata_sha256": "2f24b92a676323bc60dcefe696518a956e833c41874cb0e49dec4b797d130766",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11678",
      "published": "2026-10-08T10:52:26Z",
      "updated": "2026-10-08T10:52:26Z",
      "revision": 1,
      "metadata_sha256": "0d6d950f7d04f0935b2fd14a3ea2a3858a5d3ff5322cc73c23bda302c8703a7a",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.11659",
      "published": "2026-10-08T10:36:00Z",
      "updated": "2026-10-08T10:36:00Z",
      "revision": 1,
      "metadata_sha256": "b5f21a17c8e17af40a5798f013c77d366aeac8414b3a56ab7b13fcb18bbcbd5b",
      "repository_status": "implemented",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.11638",
      "published": "2026-10-08T10:15:55Z",
      "updated": "2026-10-08T10:15:55Z",
      "revision": 1,
      "metadata_sha256": "0692049dc2d9e273b206d38274f40688baeaf7dd55a0ce315657371ed77f31c1",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.11599",
      "published": "2026-10-08T09:44:08Z",
      "updated": "2026-10-08T09:44:08Z",
      "revision": 1,
      "metadata_sha256": "e89d2985fc2a39cd60ec448ea75e3a050ae5020b2a5cc96e6b6104fdeacd1b07",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11543",
      "published": "2026-10-08T09:11:17Z",
      "updated": "2026-10-08T09:11:17Z",
      "revision": 1,
      "metadata_sha256": "7fae98d96541f972d1e00b7471d94c7b1eee56289dff0a26a00c79f2dbdca6b6",
      "repository_status": "reviewed",
      "matched_queries": [
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.11519",
      "published": "2026-10-08T08:52:55Z",
      "updated": "2026-10-08T08:52:55Z",
      "revision": 1,
      "metadata_sha256": "8bc09374ed350de2c613d268ca5635dc0929dce43db15d4a0db8665ea4ed2d26",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11464",
      "published": "2026-10-08T08:13:53Z",
      "updated": "2026-10-08T08:13:53Z",
      "revision": 1,
      "metadata_sha256": "fba1affb6617866ae79235af69ba1bcca5ab0405213a31b5f7e4f0c29c9594d6",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.11461",
      "published": "2026-10-08T08:12:28Z",
      "updated": "2026-10-08T08:12:28Z",
      "revision": 1,
      "metadata_sha256": "41939f222adac35de8be051029eb1131474faf48c2eca5b86c143452e1893dc1",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11451",
      "published": "2026-10-08T08:04:22Z",
      "updated": "2026-10-10T03:10:01Z",
      "revision": 2,
      "metadata_sha256": "aa345fb427bd0a3e403fb3d30b4bb9a801e3e823c76601128c4e5ed5c191415b",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.11423",
      "published": "2026-10-08T07:48:55Z",
      "updated": "2026-10-08T07:48:55Z",
      "revision": 1,
      "metadata_sha256": "9ca9214a68a2687707abc355e9a16ac23606de1d866bad5cb8f53602381772c3",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11373",
      "published": "2026-10-08T07:06:52Z",
      "updated": "2026-10-08T07:06:52Z",
      "revision": 1,
      "metadata_sha256": "0827d750c460384c90861fc4877480859c475f1a6252e5c61686f72473cff519",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11371",
      "published": "2026-10-08T07:03:24Z",
      "updated": "2026-10-08T07:03:24Z",
      "revision": 1,
      "metadata_sha256": "5cf927f50a745c26611fcf66449997b3ea7bb14761e7e7622955a6374b9dfe81",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.11366",
      "published": "2026-10-08T06:58:30Z",
      "updated": "2026-10-08T06:58:30Z",
      "revision": 1,
      "metadata_sha256": "9e741eb995149d32951bf1aa3e8e3b2046eab2c2b519eca18b33d716deed4261",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11354",
      "published": "2026-10-08T06:47:41Z",
      "updated": "2026-10-13T03:43:28Z",
      "revision": 2,
      "metadata_sha256": "a21c65a9bb6e335e70eba78500b3c52b2018d2c77352d14891d2bdaadd7e99a3",
      "repository_status": "reviewed",
      "matched_queries": [
        "process-reward",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11352",
      "published": "2026-10-08T06:45:24Z",
      "updated": "2026-10-08T06:45:24Z",
      "revision": 1,
      "metadata_sha256": "da5cdf5b127a2c1b1d5229bd097665efdd562f31bc383e38333f89c6fbde6f44",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11332",
      "published": "2026-10-08T06:28:38Z",
      "updated": "2026-10-08T06:28:38Z",
      "revision": 1,
      "metadata_sha256": "c360d6ee13aa5f69f76803e80f41c201e4fbab7b17c53c2dc1f4c9fe9145a6d4",
      "repository_status": "implemented",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11291",
      "published": "2026-10-08T05:54:03Z",
      "updated": "2026-10-08T05:54:03Z",
      "revision": 1,
      "metadata_sha256": "3f8071ac955584bd77b45ceccad3e608732cd741e09750e50bccdb4d0778a8f4",
      "repository_status": "implemented",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11281",
      "published": "2026-10-08T05:48:31Z",
      "updated": "2026-10-08T05:48:31Z",
      "revision": 1,
      "metadata_sha256": "98a642e31d9ba5415c8852b14e22103cf3efc2fc15bc7c81b509e1d5aa4a7213",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.11247",
      "published": "2026-10-08T04:52:05Z",
      "updated": "2026-10-08T04:52:05Z",
      "revision": 1,
      "metadata_sha256": "f3be12ca6ea8a3e6e45e459103de6090121cbf70b19dad0713f8e75df008bfbf",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.11226",
      "published": "2026-10-08T04:22:29Z",
      "updated": "2026-10-08T04:22:29Z",
      "revision": 1,
      "metadata_sha256": "e3b4981af6e528ca510ad1cd8d3ebae11707f316c4f412c3ad972162a9ce9dee",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.11183",
      "published": "2026-10-08T03:40:48Z",
      "updated": "2026-10-08T03:40:48Z",
      "revision": 1,
      "metadata_sha256": "a11c25f946a61776de2daf68a81d3619048960dc32851e53116bfb5173f5e4b9",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.11167",
      "published": "2026-10-08T03:24:55Z",
      "updated": "2026-10-08T03:24:55Z",
      "revision": 1,
      "metadata_sha256": "b715d3566db2ed30f64d77b125170b9b59a09bc368de3d90c5f93f93e314ad1c",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11152",
      "published": "2026-10-08T03:15:00Z",
      "updated": "2026-10-14T08:09:07Z",
      "revision": 3,
      "metadata_sha256": "fded8ddc8afa9e5026e08591ea42b287aa8bb0b799b18dbbf57b60a3f61b6f89",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "process-reward",
        "reward-model",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.11111",
      "published": "2026-10-08T02:33:37Z",
      "updated": "2026-10-08T02:33:37Z",
      "revision": 1,
      "metadata_sha256": "ff83fe71bd72772c4b9f5a82de0baa3b270d8c47f559d420820355219191668f",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.11064",
      "published": "2026-10-08T01:25:16Z",
      "updated": "2026-10-09T02:22:30Z",
      "revision": 2,
      "metadata_sha256": "ee2e6e8026e3a0089085294aad2dcf8416c546b135183d66ca52774022ca816d",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.11030",
      "published": "2026-10-08T00:23:22Z",
      "updated": "2026-10-14T02:16:32Z",
      "revision": 2,
      "metadata_sha256": "97f7b61771843446d400b5d98bfc32aa2e0109f5ff83c812dcfc808ae86ced2f",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10974",
      "published": "2026-10-07T22:55:15Z",
      "updated": "2026-10-07T22:55:15Z",
      "revision": 1,
      "metadata_sha256": "8487f28adbc0e6a18ec1ef5cc06e53dbefa4e9e9b176b997ad12b6e6f127ec6a",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.10947",
      "published": "2026-10-07T21:52:33Z",
      "updated": "2026-10-07T21:52:33Z",
      "revision": 1,
      "metadata_sha256": "e58335d13d76f7ff27dee232141aae11a27af31ea5bdeb3b2b81a1cc98e10f28",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10942",
      "published": "2026-10-07T21:46:10Z",
      "updated": "2026-10-07T21:46:10Z",
      "revision": 1,
      "metadata_sha256": "3b752a391fe90e875590eb924bb1dc3de8c92973e2edb0182258cea9e73b8b43",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.10932",
      "published": "2026-10-07T21:41:33Z",
      "updated": "2026-10-07T21:41:33Z",
      "revision": 1,
      "metadata_sha256": "4a84dc68f12784a1e963083c6d64a5264baa31c93dfaa710e3400ce4ea87a642",
      "repository_status": "reviewed",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.10878",
      "published": "2026-10-07T20:29:29Z",
      "updated": "2026-10-07T20:29:29Z",
      "revision": 1,
      "metadata_sha256": "caa1021b5789cd94fb8ab02199f8bc02c2ee756ae5ca4577a0e0090f07444002",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10868",
      "published": "2026-10-07T20:13:03Z",
      "updated": "2026-10-07T20:13:03Z",
      "revision": 1,
      "metadata_sha256": "04a054a922d90327b2bd9cfc2970337c6526bad7a9eee914b31b01cc1cfa5d5d",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10854",
      "published": "2026-10-07T19:59:07Z",
      "updated": "2026-10-07T19:59:07Z",
      "revision": 1,
      "metadata_sha256": "01545a0a5b30dab3691d642cc7d5a38c273ca0fd64e1e3ea435fde1a5b4e6ee9",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.10848",
      "published": "2026-10-07T19:51:59Z",
      "updated": "2026-10-07T19:51:59Z",
      "revision": 1,
      "metadata_sha256": "7fef2683183dbda156cf542b1ea2d5d844982ea1b55b1a2a05abe6393b91c185",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10833",
      "published": "2026-10-07T19:35:08Z",
      "updated": "2026-10-07T19:35:08Z",
      "revision": 1,
      "metadata_sha256": "8f4535bcadd60f48a1d89cc11b3aee928aec81b11c677a5e417fbc2e8115d1e5",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10787",
      "published": "2026-10-07T18:45:56Z",
      "updated": "2026-10-12T08:50:46Z",
      "revision": 2,
      "metadata_sha256": "462c51d69af0d59611d9331fe767dac21636b91d34348f9b7811b8c5403ef481",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.10536",
      "published": "2026-10-07T17:59:26Z",
      "updated": "2026-10-07T17:59:26Z",
      "revision": 1,
      "metadata_sha256": "c1a9d66b2a1a5c6979fe02fb847ff5f0f200d6dafbd6f48b829a3bf380d42d68",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10526",
      "published": "2026-10-07T17:57:38Z",
      "updated": "2026-10-07T17:57:38Z",
      "revision": 1,
      "metadata_sha256": "309f011f5f0b8deeb7cf519f1f70357eab4a15aa3f52be10d8b0d6dee3a6a34f",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.10506",
      "published": "2026-10-07T17:51:07Z",
      "updated": "2026-10-07T17:51:07Z",
      "revision": 1,
      "metadata_sha256": "6246640a25686ab175f894ffbbb86b1cb7037305c1ed79caa16f3b8841118360",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10447",
      "published": "2026-10-07T17:19:19Z",
      "updated": "2026-10-07T17:19:19Z",
      "revision": 1,
      "metadata_sha256": "a5f44f049359e35156c56e874137dbb3d3524c51738c5a3ef76bc17e21d33856",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10426",
      "published": "2026-10-07T17:06:59Z",
      "updated": "2026-10-07T17:06:59Z",
      "revision": 1,
      "metadata_sha256": "4e1c273663338a921d1e41c1f4934b3331a8b5967b8576d8285e6d6a5017173f",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.10422",
      "published": "2026-10-07T17:01:37Z",
      "updated": "2026-10-07T17:01:37Z",
      "revision": 1,
      "metadata_sha256": "449df276a1ff7e2138eba63c8bafce48ea10bde6f99086db9ed092b2f48c8fa7",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.10411",
      "published": "2026-10-07T16:56:29Z",
      "updated": "2026-10-07T16:56:29Z",
      "revision": 1,
      "metadata_sha256": "f9d0dea781d4d1885c8e638c1cdad56e21cd80aad32ef6ecc81db8cf1130c3ad",
      "repository_status": "reviewed",
      "matched_queries": [
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.10407",
      "published": "2026-10-07T16:55:05Z",
      "updated": "2026-10-07T16:55:05Z",
      "revision": 1,
      "metadata_sha256": "a72d45977e4e096e898fd71e60c2864555789516550539f1ddcfd718074e2428",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.10273",
      "published": "2026-10-07T15:40:47Z",
      "updated": "2026-10-07T15:40:47Z",
      "revision": 1,
      "metadata_sha256": "58cce7ac462799f04b685c6bca95ef4bf70aa970ba573c7d0605f80420d93cee",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10179",
      "published": "2026-10-07T14:48:47Z",
      "updated": "2026-10-07T14:48:47Z",
      "revision": 1,
      "metadata_sha256": "a7246a4f9548a6058ca321f42272aa3df031eef95d236f81d88c5c183ca755bf",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10641",
      "published": "2026-10-07T14:39:18Z",
      "updated": "2026-10-07T14:39:18Z",
      "revision": 1,
      "metadata_sha256": "1e9a155e22600f1caffdb2ffc6a2a44ba6bb48c4a3ec8bf3c91104591485bddf",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.10145",
      "published": "2026-10-07T14:23:32Z",
      "updated": "2026-10-07T14:23:32Z",
      "revision": 1,
      "metadata_sha256": "e32a650f6633d4084e13e5ffff2fd8f9c926a2a0e04e9e64ae98d890d40ebc16",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.10092",
      "published": "2026-10-07T13:50:50Z",
      "updated": "2026-10-07T13:50:50Z",
      "revision": 1,
      "metadata_sha256": "f24c764c45e6955057ab59e953f8d0619c1abd5c11d20c888dee60217a2aa628",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.10080",
      "published": "2026-10-07T13:44:55Z",
      "updated": "2026-10-13T18:51:37Z",
      "revision": 2,
      "metadata_sha256": "ddfb2d474993cf747486e62c2937a6f8cefb1024bed56d0aa20745873ba144d1",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.09985",
      "published": "2026-10-07T12:50:08Z",
      "updated": "2026-10-07T12:50:08Z",
      "revision": 1,
      "metadata_sha256": "074b8e4dbbbe01026811768b39c6048c56849f542b0f69c9a28f60455ad8d88c",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09934",
      "published": "2026-10-07T12:18:40Z",
      "updated": "2026-10-07T12:18:40Z",
      "revision": 1,
      "metadata_sha256": "10927f7b9ebafda898223d37eb00270c9e0e2ffc53a295c299365a7ca4efc487",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.09914",
      "published": "2026-10-07T12:05:33Z",
      "updated": "2026-10-07T12:05:33Z",
      "revision": 1,
      "metadata_sha256": "b716486396a45add2e5aa4d639952529a18e73b966c02d0e85b7412a28147aa1",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.09906",
      "published": "2026-10-07T12:00:51Z",
      "updated": "2026-10-07T12:00:51Z",
      "revision": 1,
      "metadata_sha256": "5e308347d03ee4352bb281d98de69397dcee408b2120dc5ca6f0dbc92f0fad75",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09858",
      "published": "2026-10-07T11:14:26Z",
      "updated": "2026-10-07T11:14:26Z",
      "revision": 1,
      "metadata_sha256": "a4a97eb2dd9e30eea74ba36ecb9ba0c56d7032a74716eda65f5006d933ca9929",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.09841",
      "published": "2026-10-07T11:03:58Z",
      "updated": "2026-10-07T11:03:58Z",
      "revision": 1,
      "metadata_sha256": "2fda5d67047edfe4fa6101e4947584770dd15c6a7472e24de39a9c2a23d4b2d0",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.09835",
      "published": "2026-10-07T11:01:01Z",
      "updated": "2026-10-07T11:01:01Z",
      "revision": 1,
      "metadata_sha256": "475e4809ff0d16dcd6ddb5466c41a45f1fd239168a4c289c739367a1603dde50",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.09804",
      "published": "2026-10-07T10:23:17Z",
      "updated": "2026-10-07T10:23:17Z",
      "revision": 1,
      "metadata_sha256": "47f7290e66aabb48a1aca93dabdd699a9ef64f047951906ebbc07c7f67e19e51",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "process-reward",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09795",
      "published": "2026-10-07T10:10:01Z",
      "updated": "2026-10-07T10:10:01Z",
      "revision": 1,
      "metadata_sha256": "e2aab1f2e1c1a496075808fdf89c191fa0c97a012816804d14606a35cae64654",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09788",
      "published": "2026-10-07T10:05:06Z",
      "updated": "2026-10-08T02:03:42Z",
      "revision": 2,
      "metadata_sha256": "cd43138f98128b80088220aafd4ef92f84b2392449149bc79a1406b9f36f252a",
      "repository_status": "reviewed",
      "matched_queries": [
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.14063",
      "published": "2026-10-07T09:00:25Z",
      "updated": "2026-10-07T09:00:25Z",
      "revision": 1,
      "metadata_sha256": "d6fb702df423e5eb557646ba174a74f6696d5d7633d38add2520562fe2b7059c",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.10623",
      "published": "2026-10-07T08:54:30Z",
      "updated": "2026-10-07T08:54:30Z",
      "revision": 1,
      "metadata_sha256": "04da8866970bf0626dafb16f1017677fdfe03856f3f7d7f11db3330f2ef9de12",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.09684",
      "published": "2026-10-07T08:46:56Z",
      "updated": "2026-10-07T08:46:56Z",
      "revision": 1,
      "metadata_sha256": "6172da095d102b7f6cee91118b160fa076f07e1ec0d1f5308e4bb41affffb8e0",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.09665",
      "published": "2026-10-07T08:31:37Z",
      "updated": "2026-10-07T08:31:37Z",
      "revision": 1,
      "metadata_sha256": "e64a47a59d3edb75341fec9a9ce58c45722159f5a00f09957ce3f23eff6c2c42",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.09647",
      "published": "2026-10-07T08:22:30Z",
      "updated": "2026-10-07T08:22:30Z",
      "revision": 1,
      "metadata_sha256": "faab9f37fe37d3368fbf397e17419b313c7f8f8c0cf719427c55dc6209519bd7",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.09639",
      "published": "2026-10-07T08:15:10Z",
      "updated": "2026-10-07T08:15:10Z",
      "revision": 1,
      "metadata_sha256": "83abf7850860898bf44f962f06996f4a276ee0576506009b45344ec04e67476f",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09597",
      "published": "2026-10-07T07:43:49Z",
      "updated": "2026-10-07T07:43:49Z",
      "revision": 1,
      "metadata_sha256": "51f5024a5b608df530bc01986b8885d6f2ef309e6883bfc7207626e0ae9ebd2f",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09587",
      "published": "2026-10-07T07:31:33Z",
      "updated": "2026-10-07T07:31:33Z",
      "revision": 1,
      "metadata_sha256": "0696697f6f42a4faab62e7302e4f87e797dcd0ec8d21057504165390dac630e3",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.09563",
      "published": "2026-10-07T07:04:22Z",
      "updated": "2026-10-11T08:28:40Z",
      "revision": 2,
      "metadata_sha256": "540508da0c35b36e8d4eda2b71d9e667736365748af59843671e9832185af2ef",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09517",
      "published": "2026-10-07T06:15:23Z",
      "updated": "2026-10-07T06:15:23Z",
      "revision": 1,
      "metadata_sha256": "5423be8ea90e3adb8de4a637ddc901dfbcf09483377caef25c348b00a1d6aa02",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.09471",
      "published": "2026-10-07T05:26:15Z",
      "updated": "2026-10-12T07:48:22Z",
      "revision": 3,
      "metadata_sha256": "e5015005321db448d069f36cee2e86629cd35879baa3547d176c0c30b6078180",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.09458",
      "published": "2026-10-07T05:12:42Z",
      "updated": "2026-10-12T02:25:35Z",
      "revision": 2,
      "metadata_sha256": "1ef14aaa5b000385a8e75552ae593a94cd689459e52904c36e27c1837596aec5",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09384",
      "published": "2026-10-07T03:40:44Z",
      "updated": "2026-10-07T03:40:44Z",
      "revision": 1,
      "metadata_sha256": "9243cb8a7436281b10b5d312d8be479d605aa38a49d59efb5b351f774d6a4053",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.09369",
      "published": "2026-10-07T03:22:26Z",
      "updated": "2026-10-14T05:25:20Z",
      "revision": 2,
      "metadata_sha256": "0f2d59eb661eb722f82318b637da46e828acc4e80132ef41bea10099d25ec7df",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.09355",
      "published": "2026-10-07T03:13:03Z",
      "updated": "2026-10-07T03:13:03Z",
      "revision": 1,
      "metadata_sha256": "e78e6288cc1d4f3eb14bdaf82b6650998a868fd0ed705b6a7d3489ae1b0fcc55",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.09346",
      "published": "2026-10-07T03:05:42Z",
      "updated": "2026-10-07T03:05:42Z",
      "revision": 1,
      "metadata_sha256": "920714f72f76f22bed66e493698ba3a703b6ffce96598169a1278d2913c39add",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09337",
      "published": "2026-10-07T02:53:26Z",
      "updated": "2026-10-07T02:53:26Z",
      "revision": 1,
      "metadata_sha256": "204d0898cbb297d035de5030aa8356c8c01d7afd1ca612a642c3d031f3dd47bd",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09328",
      "published": "2026-10-07T02:34:09Z",
      "updated": "2026-10-07T02:34:09Z",
      "revision": 1,
      "metadata_sha256": "fcf9b995fd0358043298fb63c925770d4d42ef9f153a1429995e71d87a615c54",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09247",
      "published": "2026-10-07T00:20:45Z",
      "updated": "2026-10-07T00:20:45Z",
      "revision": 1,
      "metadata_sha256": "0996a9503bc11a38098cf91e8b5b68d2a4e35191396db190147fb93f99687662",
      "repository_status": "reviewed",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.09227",
      "published": "2026-10-06T23:44:32Z",
      "updated": "2026-10-06T23:44:32Z",
      "revision": 1,
      "metadata_sha256": "c1689654b72311b0b27bf5321db8a41f93e704de73c8d86a2a74c67a279e1eaf",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.09209",
      "published": "2026-10-06T23:10:21Z",
      "updated": "2026-10-06T23:10:21Z",
      "revision": 1,
      "metadata_sha256": "2b14bebe5727e5b9edb8f2ef3a347754105420daa8fcc7b70781589abc028d7d",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.09179",
      "published": "2026-10-06T22:30:58Z",
      "updated": "2026-10-06T22:30:58Z",
      "revision": 1,
      "metadata_sha256": "3955ebd9046d5b11bac57a0a967498d464259dbffffc7996894439144e68caee",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.09108",
      "published": "2026-10-06T20:59:21Z",
      "updated": "2026-10-06T20:59:21Z",
      "revision": 1,
      "metadata_sha256": "7e8c2d8a49e58ab3e53a4b010c31fe245ff20975c8f4e714e9e651492427859c",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.09074",
      "published": "2026-10-06T20:18:17Z",
      "updated": "2026-10-06T20:18:17Z",
      "revision": 1,
      "metadata_sha256": "d6987f36a0be1e7d7a36500a38545bdeee73d44fe2ba582a7044d04b7debb79f",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.10592",
      "published": "2026-10-06T18:35:26Z",
      "updated": "2026-10-06T18:35:26Z",
      "revision": 1,
      "metadata_sha256": "4d2b9fdc11794933122b73fa6fc8cb9531b2664919c6282ba1beb5be442277b1",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.08963",
      "published": "2026-10-06T18:30:42Z",
      "updated": "2026-10-06T18:30:42Z",
      "revision": 1,
      "metadata_sha256": "2d25b99bc83aa9c6e4b6342e17ac898f4855acf467b44c32cbf9d19dbb0843e1",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.08959",
      "published": "2026-10-06T18:25:23Z",
      "updated": "2026-10-13T07:31:01Z",
      "revision": 2,
      "metadata_sha256": "a18edd02c8c75d737951b33bf2b98d38310c0f226cd59984e2b989bb0edbb290",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "policy-llm-abbreviation",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.08781",
      "published": "2026-10-06T17:59:01Z",
      "updated": "2026-10-06T17:59:01Z",
      "revision": 1,
      "metadata_sha256": "86605c8c70da1032955c2d3ee08d6a78bb3b3f7ead52684cec66f10421bda36e",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.08778",
      "published": "2026-10-06T17:58:18Z",
      "updated": "2026-10-06T17:58:18Z",
      "revision": 1,
      "metadata_sha256": "fe9411a2b51a9d9b3774bf845ad73dc1140ee21a0dfe727b81cba8edbc92031c",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.08773",
      "published": "2026-10-06T17:56:43Z",
      "updated": "2026-10-06T17:56:43Z",
      "revision": 1,
      "metadata_sha256": "36ea6c51be3bf491a046b49ab2361b05ac7680c6968c2b91755d01384b71d3b6",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.08670",
      "published": "2026-10-06T16:52:23Z",
      "updated": "2026-10-06T16:52:23Z",
      "revision": 1,
      "metadata_sha256": "73d9fbd7e2b2314f5d341291754eb3a86c57fc554212f15bc8f29dfd528d8cac",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.08652",
      "published": "2026-10-06T16:38:03Z",
      "updated": "2026-10-13T22:14:40Z",
      "revision": 2,
      "metadata_sha256": "3073fdb3744361dfa21f4abbb49c2c2b962afd69db0fadf95d5ed64ee02f9bff",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18886",
      "published": "2026-10-06T15:52:46Z",
      "updated": "2026-10-06T15:52:46Z",
      "revision": 1,
      "metadata_sha256": "a337c682676d86690c0026f9dc829484581b63ebbd75251aa9cdce139810c528",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.08561",
      "published": "2026-10-06T15:43:08Z",
      "updated": "2026-10-06T15:43:08Z",
      "revision": 1,
      "metadata_sha256": "2ad1378ff8c2d614a521f8aed32a4617f1b48f7fd2d68a35351415b7f66d78a5",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.08448",
      "published": "2026-10-06T14:37:22Z",
      "updated": "2026-10-06T14:37:22Z",
      "revision": 1,
      "metadata_sha256": "36807fd3783cd6b4a08173318342d778759db196d0c21d5beb1f911b188660a5",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.08402",
      "published": "2026-10-06T14:15:11Z",
      "updated": "2026-10-06T14:15:11Z",
      "revision": 1,
      "metadata_sha256": "ee2e66fa0d63011885a350a439c706726b08530157828a349e86be9bfda445bc",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.08398",
      "published": "2026-10-06T14:13:31Z",
      "updated": "2026-10-06T14:13:31Z",
      "revision": 1,
      "metadata_sha256": "946f85c5fb0f33a874b969da72d212def7cb3f8b046fe52b96e7d6aea6271b0d",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.08112",
      "published": "2026-10-06T10:35:13Z",
      "updated": "2026-10-06T10:35:13Z",
      "revision": 1,
      "metadata_sha256": "1e85b324bfcafbb1c38a5ae8baf1f240b8e664293b6ca8c2a960dd843b5ce39a",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.08108",
      "published": "2026-10-06T10:31:54Z",
      "updated": "2026-10-06T10:31:54Z",
      "revision": 1,
      "metadata_sha256": "a59d35a2967990b14c1bfa712ecaa2f53201eb1333185bcdbf902bb7fe2e9318",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.08082",
      "published": "2026-10-06T10:14:16Z",
      "updated": "2026-10-06T10:14:16Z",
      "revision": 1,
      "metadata_sha256": "35379c7c596691acb894233b663de0d7369a26bcff5794a2f2bab70e2166426e",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.08078",
      "published": "2026-10-06T10:07:19Z",
      "updated": "2026-10-13T18:56:02Z",
      "revision": 2,
      "metadata_sha256": "fa983b9dd9390ce693c675a4772b4391353344e76a8b2caa184a1b5ea565518b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.08077",
      "published": "2026-10-06T10:06:47Z",
      "updated": "2026-10-14T08:03:34Z",
      "revision": 3,
      "metadata_sha256": "704ee396cb0c5985bd40158232143f84d199b08275f3c5aed431d8861ecb2ad4",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07898",
      "published": "2026-10-06T07:44:12Z",
      "updated": "2026-10-06T07:44:12Z",
      "revision": 1,
      "metadata_sha256": "d3ca04948494faeb23c3028ca72ef15ce00ccafa8c2025c36cbc03615f44d2b0",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.07874",
      "published": "2026-10-06T07:25:03Z",
      "updated": "2026-10-06T07:25:03Z",
      "revision": 1,
      "metadata_sha256": "b235470a5b7c571982990958cdc8f158be6f2c0b5b44fc47b407945a5755497a",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07863",
      "published": "2026-10-06T07:09:54Z",
      "updated": "2026-10-06T07:09:54Z",
      "revision": 1,
      "metadata_sha256": "8a76ea084c11c955f54f077d1574fc622f34fea77862d1cdec7d4b1c65ac2869",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07853",
      "published": "2026-10-06T06:58:35Z",
      "updated": "2026-10-14T09:28:41Z",
      "revision": 2,
      "metadata_sha256": "4d16b1a2393cb2fac75e962d51b92e4d3ba328833568ee591cc6413d92fa89a6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.07842",
      "published": "2026-10-06T06:45:39Z",
      "updated": "2026-10-06T06:45:39Z",
      "revision": 1,
      "metadata_sha256": "19d5fa379907b01d58a6ca167b7f2a3c305b2cc9077bb79c85a501f7d4a5d8ff",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.07781",
      "published": "2026-10-06T05:17:10Z",
      "updated": "2026-10-06T05:17:10Z",
      "revision": 1,
      "metadata_sha256": "9a8d5a280051aa76dcec980e043e3bf485fe45c8e5400d5a5abc75a96b3a70a4",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.07767",
      "published": "2026-10-06T05:03:47Z",
      "updated": "2026-10-09T04:13:24Z",
      "revision": 2,
      "metadata_sha256": "265ade182337828b242348cb9af8d864cf61eefe672b04dd92ad062ba80e5ff3",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.07739",
      "published": "2026-10-06T04:36:07Z",
      "updated": "2026-10-06T04:36:07Z",
      "revision": 1,
      "metadata_sha256": "25ca3ce34693e5f2ed1d4091b82fd407e001a48a2c3ba7c842aa8c27396910c7",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.07731",
      "published": "2026-10-06T04:29:29Z",
      "updated": "2026-10-06T04:29:29Z",
      "revision": 1,
      "metadata_sha256": "7aa04bf58a32e8e06bb6bced8c2d3f8ed596613b7345153a41392fd628c30df3",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.07730",
      "published": "2026-10-06T04:28:22Z",
      "updated": "2026-10-10T22:45:38Z",
      "revision": 2,
      "metadata_sha256": "73e87c99a3850e8bd36358e86f98cbf988faaaef58d6ab12ec0eab6a4a9e201d",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.07704",
      "published": "2026-10-06T03:53:47Z",
      "updated": "2026-10-06T03:53:47Z",
      "revision": 1,
      "metadata_sha256": "3e1adb250d63d625bd650aae568c281b9f2d32fa0c73f3cdb8b0ea46f6a7d801",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07668",
      "published": "2026-10-06T03:03:13Z",
      "updated": "2026-10-06T03:03:13Z",
      "revision": 1,
      "metadata_sha256": "cd0db7ddbd459b97ab16c67ac921b0030c02ea27aab55e2c6f79bc40301ae2e3",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.07657",
      "published": "2026-10-06T02:52:51Z",
      "updated": "2026-10-11T22:08:34Z",
      "revision": 2,
      "metadata_sha256": "181f524879144d26e745a7151dbd05a36d5822cc25b5e1065173b206918efe9f",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07654",
      "published": "2026-10-06T02:50:07Z",
      "updated": "2026-10-06T02:50:07Z",
      "revision": 1,
      "metadata_sha256": "141936ada279dc4229903f8f1af4312e7fc9c4f9e9014989d9d4b3ab2ce88ac9",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.07587",
      "published": "2026-10-06T01:24:56Z",
      "updated": "2026-10-07T11:21:43Z",
      "revision": 2,
      "metadata_sha256": "96b37a5ca7b5e39f10e3cb60e72499a11051b55db2c05a3b8f22f502fe5727b7",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.07580",
      "published": "2026-10-06T01:14:09Z",
      "updated": "2026-10-06T01:14:09Z",
      "revision": 1,
      "metadata_sha256": "8488700b659b2c24c608aef9326c1caaba0205ca9227db30a05282193982706d",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07563",
      "published": "2026-10-06T00:50:28Z",
      "updated": "2026-10-06T00:50:28Z",
      "revision": 1,
      "metadata_sha256": "ada30b732191e177879dbf607bc39b0cfe37e2948c7b595bcf638b72edb75bb5",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07545",
      "published": "2026-10-06T00:21:08Z",
      "updated": "2026-10-14T08:03:16Z",
      "revision": 2,
      "metadata_sha256": "2dfd2776adaff20f2f8a6042d91faedd0fb3580ddd0a248fca6ac8a3ba0b2c75",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.07522",
      "published": "2026-10-05T23:41:48Z",
      "updated": "2026-10-05T23:41:48Z",
      "revision": 1,
      "metadata_sha256": "d7d519dd46f701f5c33911f88c91d999fa92c09c18dcbc9a0a830c887f34194d",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.07518",
      "published": "2026-10-05T23:28:45Z",
      "updated": "2026-10-05T23:28:45Z",
      "revision": 1,
      "metadata_sha256": "14ad745c3b98827652a93471fa95d09b406ca0008995e3ba896f5fe8d64d88eb",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.07457",
      "published": "2026-10-05T22:06:04Z",
      "updated": "2026-10-05T22:06:04Z",
      "revision": 1,
      "metadata_sha256": "1e01347e55c14399c4fdc09eca44179f8709bb6020daf6e62022a31484c46e84",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.07405",
      "published": "2026-10-05T21:16:32Z",
      "updated": "2026-10-05T21:16:32Z",
      "revision": 1,
      "metadata_sha256": "a74cc22bdfdf3998c608db74b8d3b13a243181e9138ead6ade46fd69a26e87b4",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07349",
      "published": "2026-10-05T20:19:04Z",
      "updated": "2026-10-05T20:19:04Z",
      "revision": 1,
      "metadata_sha256": "3c316e7229fbd250efb9c7b06daf52df0e6f876d2109366e397ddce665bdd867",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07332",
      "published": "2026-10-05T20:06:47Z",
      "updated": "2026-10-05T20:06:47Z",
      "revision": 1,
      "metadata_sha256": "5bef92547cccd78c3d4d22646ba9a23298859dafc5ac2b0b817c8dd9b87a0aee",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.07258",
      "published": "2026-10-05T18:56:56Z",
      "updated": "2026-10-05T18:56:56Z",
      "revision": 1,
      "metadata_sha256": "a2d9fc0767232891411fe1aa79d0ffec798576f33afb39d6afdd47d521896ef1",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07247",
      "published": "2026-10-05T18:48:00Z",
      "updated": "2026-10-05T18:48:00Z",
      "revision": 1,
      "metadata_sha256": "41bd954dae11d075f1eecaf707a9baebb037475d6b198ac528eea2002c774ee6",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.07226",
      "published": "2026-10-05T18:34:49Z",
      "updated": "2026-10-05T18:34:49Z",
      "revision": 1,
      "metadata_sha256": "ef66cf2bf2e9eed2ffa55fc8a046a8d2d52e5632b4cd25e3a162656f0349c4ae",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.07212",
      "published": "2026-10-05T18:26:21Z",
      "updated": "2026-10-05T18:26:21Z",
      "revision": 1,
      "metadata_sha256": "20a7954a96e03e11e5eca0899a1051ce3645e38fd76a64dec9ed7e6412d6d707",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07177",
      "published": "2026-10-05T18:01:37Z",
      "updated": "2026-10-05T18:01:37Z",
      "revision": 1,
      "metadata_sha256": "929ae0c0ce1d1577e1ded1761a82c24e4eef5c5350a6546ecc64b9452f2c7d2d",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.06851",
      "published": "2026-10-05T17:59:52Z",
      "updated": "2026-10-05T17:59:52Z",
      "revision": 1,
      "metadata_sha256": "c47de5f59dbf7a54464cff1f099397deb05fafe4afa3d4de80ee46c3ce2d5032",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.06844",
      "published": "2026-10-05T17:59:17Z",
      "updated": "2026-10-05T17:59:17Z",
      "revision": 1,
      "metadata_sha256": "7dcba83bd77d298890f40cf36170e16ae309e95e17eb9b4acb6db82b76c7c887",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.06843",
      "published": "2026-10-05T17:59:11Z",
      "updated": "2026-10-05T17:59:11Z",
      "revision": 1,
      "metadata_sha256": "7c84a13657337a25c566e3ad2215ecb7c9f40b0fdd5513683293dcd0bac06b2c",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06833",
      "published": "2026-10-05T17:58:15Z",
      "updated": "2026-10-05T17:58:15Z",
      "revision": 1,
      "metadata_sha256": "da8ed942d153beb260bcf0934364fcadc07395a405b2d5f9e977b57f9e9657db",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.06830",
      "published": "2026-10-05T17:58:06Z",
      "updated": "2026-10-05T17:58:06Z",
      "revision": 1,
      "metadata_sha256": "84e07a35c3979bb7363074137a98469663f21dd97c97c50d9a18414de90684aa",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.06829",
      "published": "2026-10-05T17:57:51Z",
      "updated": "2026-10-05T17:57:51Z",
      "revision": 1,
      "metadata_sha256": "53d7f084984c69c3ff176e2b61677866185ceb217b19281a91ab1f42a220f7e8",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.06804",
      "published": "2026-10-05T17:53:30Z",
      "updated": "2026-10-05T17:53:30Z",
      "revision": 1,
      "metadata_sha256": "29ec79e787e6cc7183b6138ae13772f7f485bd42459853ff12ae11f5d0dc2808",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06782",
      "published": "2026-10-05T17:44:26Z",
      "updated": "2026-10-05T17:44:26Z",
      "revision": 1,
      "metadata_sha256": "e11cbf4005304c779aae16b058634ea54788d81592a4332107e3c873700ba274",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.07121",
      "published": "2026-10-05T17:30:54Z",
      "updated": "2026-10-05T17:30:54Z",
      "revision": 1,
      "metadata_sha256": "d6188ade60b28c59732d64a44109751ab4abd89e024dba37f60686f81e53583c",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.06744",
      "published": "2026-10-05T17:22:23Z",
      "updated": "2026-10-05T17:22:23Z",
      "revision": 1,
      "metadata_sha256": "93ba238eaf98585ddd50c6870fa8df1ebf10bccbc9ba3c4e6b97651e539ce44e",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.06729",
      "published": "2026-10-05T17:16:29Z",
      "updated": "2026-10-06T17:15:34Z",
      "revision": 2,
      "metadata_sha256": "1a088e910b898bd019d647ef6436ceb15ba3863d6514ef02ca8a8dd1482632a9",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.07118",
      "published": "2026-10-05T17:11:07Z",
      "updated": "2026-10-05T17:11:07Z",
      "revision": 1,
      "metadata_sha256": "e8bafe99dfb409efa4b2e76954200a0ed3a936e8fe24165fa659b40108737efc",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.06695",
      "published": "2026-10-05T16:55:58Z",
      "updated": "2026-10-05T16:55:58Z",
      "revision": 1,
      "metadata_sha256": "1c68be2758c2ddf015dc42e157ceafa20520eb676cf1b81736949f8213d282d1",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.06685",
      "published": "2026-10-05T16:51:11Z",
      "updated": "2026-10-05T16:51:11Z",
      "revision": 1,
      "metadata_sha256": "3debbc9202e4f7458bd1bd58d4571afaa597ff5b792e97cc55afa84d75f7c76d",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06671",
      "published": "2026-10-05T16:44:02Z",
      "updated": "2026-10-05T16:44:02Z",
      "revision": 1,
      "metadata_sha256": "6844d7158d50971823915800a1ab001984fe5f5d5800b6180b12cb9ec5f54d85",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.06670",
      "published": "2026-10-05T16:44:00Z",
      "updated": "2026-10-05T16:44:00Z",
      "revision": 1,
      "metadata_sha256": "2fd0c32ac0a129979550b73cde05f3779efe2f9f02d20afd67314663c872c43a",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.06648",
      "published": "2026-10-05T16:28:29Z",
      "updated": "2026-10-05T16:28:29Z",
      "revision": 1,
      "metadata_sha256": "9dc78c3a49a05f7e834d266fc548177624a9710b1561538f7dcf803bfe26507b",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.06647",
      "published": "2026-10-05T16:28:11Z",
      "updated": "2026-10-06T21:08:03Z",
      "revision": 2,
      "metadata_sha256": "8eebb17c43e4b920223cd5bd03dfb80c8161d81e51fb5996cff2514130c75eed",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.06637",
      "published": "2026-10-05T16:25:44Z",
      "updated": "2026-10-05T16:25:44Z",
      "revision": 1,
      "metadata_sha256": "ba2462575efb37dcbfcac55c47f2ebcbc6154c7104378ab594e830f02f8b34b1",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.06450",
      "published": "2026-10-05T14:53:56Z",
      "updated": "2026-10-13T18:42:09Z",
      "revision": 2,
      "metadata_sha256": "5edf3522af92ce7b4ecfe58f41611dacf4aa22d7394a5c330b9842b89a23a133",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.06446",
      "published": "2026-10-05T14:50:58Z",
      "updated": "2026-10-05T14:50:58Z",
      "revision": 1,
      "metadata_sha256": "b3d24160a41a2e34f2473d5dad325f537658d5959ae05e1567d17f4e7c17d7c9",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.06439",
      "published": "2026-10-05T14:46:35Z",
      "updated": "2026-10-05T14:46:35Z",
      "revision": 1,
      "metadata_sha256": "a03f3078ade4bfcf9be7ef0bf24472d6189ad53729b59ec25dd467016555b9f1",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06360",
      "published": "2026-10-05T13:59:39Z",
      "updated": "2026-10-05T13:59:39Z",
      "revision": 1,
      "metadata_sha256": "c4252323e3257eefbe56148dcfe8e9b652a17b806a692a1de5e58909c3c11f6e",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06269",
      "published": "2026-10-05T13:04:05Z",
      "updated": "2026-10-12T22:19:47Z",
      "revision": 2,
      "metadata_sha256": "4357dc897c7fb924db1834aa8eb3df394b1afcb73571de8bcdbe4fb32198d628",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06204",
      "published": "2026-10-05T12:17:22Z",
      "updated": "2026-10-05T12:17:22Z",
      "revision": 1,
      "metadata_sha256": "e78b66e348d4cb39c0a1b5d125b4cda46a54731844914f3fc01014c714d27eda",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.06105",
      "published": "2026-10-05T10:36:57Z",
      "updated": "2026-10-05T10:36:57Z",
      "revision": 1,
      "metadata_sha256": "1f9924ffe8615dcb6fde63d2e3accab5e53dab072f4c4e80e5b49239d3d85fef",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06019",
      "published": "2026-10-05T09:18:27Z",
      "updated": "2026-10-05T09:18:27Z",
      "revision": 1,
      "metadata_sha256": "ffbfbc86466d46f7f1c2a9864cb8cab17133dfba8ce064af856f077e63a41cdd",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.05998",
      "published": "2026-10-05T08:51:38Z",
      "updated": "2026-10-14T09:18:28Z",
      "revision": 2,
      "metadata_sha256": "f64c31fbb5ab828c8cfa68c03af9302761598de83d9d9c67eaafd447f7146888",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.05994",
      "published": "2026-10-05T08:48:13Z",
      "updated": "2026-10-05T08:48:13Z",
      "revision": 1,
      "metadata_sha256": "800a9f90d36efe8e763a64d2a0797bbc0c9809148ce26de9df3dd040d3883f22",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05974",
      "published": "2026-10-05T08:26:20Z",
      "updated": "2026-10-05T08:26:20Z",
      "revision": 1,
      "metadata_sha256": "2e4fefb482e6c0e9319996128afb535fd8efc0edb4c4771d47b3e137e4bdc76b",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.05966",
      "published": "2026-10-05T08:16:36Z",
      "updated": "2026-10-05T08:16:36Z",
      "revision": 1,
      "metadata_sha256": "dead27b376beaf049e2c00dbbc00f03c4f2b5c93a3d78da3fafa982ef48abd81",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.05954",
      "published": "2026-10-05T08:07:18Z",
      "updated": "2026-10-05T08:07:18Z",
      "revision": 1,
      "metadata_sha256": "a1b3a0d4bb5e9b37e9882293806ea83c47c6110100a108c0f1fdd790569845ff",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.05935",
      "published": "2026-10-05T07:51:46Z",
      "updated": "2026-10-05T07:51:46Z",
      "revision": 1,
      "metadata_sha256": "162d87f9c8e4022e5a8cedb78fa9a117ce7b56748a9ca20d55ae4dd00e4b5bff",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07062",
      "published": "2026-10-05T06:56:43Z",
      "updated": "2026-10-05T06:56:43Z",
      "revision": 1,
      "metadata_sha256": "ac827f363301d8c43b63b806e32b69cd06f63bb5d218800517e640ea08a2f312",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.05872",
      "published": "2026-10-05T06:40:34Z",
      "updated": "2026-10-05T06:40:34Z",
      "revision": 1,
      "metadata_sha256": "91ccfb21a93bd35faab45c49f221f94435ab6aebc3c71d32b85eea005e427bdd",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05833",
      "published": "2026-10-05T05:37:22Z",
      "updated": "2026-10-05T05:37:22Z",
      "revision": 1,
      "metadata_sha256": "a3798094c28915b3f1baca82727df5b7a38291b461b28771c29a6bd5e2e6060f",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.05745",
      "published": "2026-10-05T03:51:21Z",
      "updated": "2026-10-09T10:33:09Z",
      "revision": 2,
      "metadata_sha256": "50ff2334684bfb3ba6a3bcbd8c802f238d9d08a571fa873f139b79e2116f0d60",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.07043",
      "published": "2026-10-05T00:53:11Z",
      "updated": "2026-10-09T03:38:25Z",
      "revision": 2,
      "metadata_sha256": "b96919fbc9f44ab5b6d5a657e947cf72ef8b33adf316319af825c9404c474e1e",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.05600",
      "published": "2026-10-04T23:05:21Z",
      "updated": "2026-10-04T23:05:21Z",
      "revision": 1,
      "metadata_sha256": "9ff66786db458e5f58045747460535df04d353999220ec46cb62528a6138da76",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.05481",
      "published": "2026-10-04T19:40:17Z",
      "updated": "2026-10-04T19:40:17Z",
      "revision": 1,
      "metadata_sha256": "89e6b7b335e256f872df59965848b8a84982d28e9a49d060de606d1aa6d553de",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.05450",
      "published": "2026-10-04T18:45:36Z",
      "updated": "2026-10-04T18:45:36Z",
      "revision": 1,
      "metadata_sha256": "591b46c97c5bfc42ce7a5b5da69dfd72e9b5fa213e7c76fa27b9c36d70fee2bd",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.05446",
      "published": "2026-10-04T18:33:23Z",
      "updated": "2026-10-04T18:33:23Z",
      "revision": 1,
      "metadata_sha256": "ea8005e2348dd8da8a8a62927316da99748f21780db86fac43a59aa938e0423b",
      "repository_status": "reviewed",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.05425",
      "published": "2026-10-04T18:06:43Z",
      "updated": "2026-10-04T18:06:43Z",
      "revision": 1,
      "metadata_sha256": "b493eb88f208711ee6be20b8f6ec57d124da69fa60860713da6e41362d8118b6",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05402",
      "published": "2026-10-04T17:37:49Z",
      "updated": "2026-10-04T17:37:49Z",
      "revision": 1,
      "metadata_sha256": "0b8b2c2340f8270a7c882b109104238e4926132d7c1619b35903fc601b795d23",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05373",
      "published": "2026-10-04T17:00:16Z",
      "updated": "2026-10-04T17:00:16Z",
      "revision": 1,
      "metadata_sha256": "f4e4e0b4d73b7ed64e2667a16dc2ca2a7c3ac0d63ce25fb66def5f8eaba3cdf2",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05367",
      "published": "2026-10-04T16:48:12Z",
      "updated": "2026-10-04T16:48:12Z",
      "revision": 1,
      "metadata_sha256": "76f33039b31c48856181e71100f6cecd7e88d1b21e9ee423e8f09ff3b216e04a",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.05329",
      "published": "2026-10-04T15:53:28Z",
      "updated": "2026-10-04T15:53:28Z",
      "revision": 1,
      "metadata_sha256": "c25f00d2b24171c5720cf90a35603d91af2be59b0d48f5379f66b7ef7aecbf48",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.07023",
      "published": "2026-10-04T15:50:42Z",
      "updated": "2026-10-04T15:50:42Z",
      "revision": 1,
      "metadata_sha256": "fb932d8f5a549b8f01854fa62ff2a307b6cf1f77a7e6e407e1db86d909860fc6",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.05308",
      "published": "2026-10-04T15:30:32Z",
      "updated": "2026-10-04T15:30:32Z",
      "revision": 1,
      "metadata_sha256": "6806985ca42c2a823e20990c897fd2c8f398d9ab87767777df6981529a8310fa",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.05303",
      "published": "2026-10-04T15:27:20Z",
      "updated": "2026-10-04T15:27:20Z",
      "revision": 1,
      "metadata_sha256": "9d9f42daba42bab08e373332f46d7a25e58f3cce04f631ee6b1e80d1db14ad75",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd",
        "policy-llm-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.05292",
      "published": "2026-10-04T15:11:16Z",
      "updated": "2026-10-04T15:11:16Z",
      "revision": 1,
      "metadata_sha256": "872e5bba2d22e09cff250b848aaff13c887f4c0e5ba3c3bf1b8b990cfbb4f9fa",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.05282",
      "published": "2026-10-04T15:03:08Z",
      "updated": "2026-10-04T15:03:08Z",
      "revision": 1,
      "metadata_sha256": "4ffae83ef684b72044617acc634a9fe884f0529357fd296597319aea61413915",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.05265",
      "published": "2026-10-04T14:35:37Z",
      "updated": "2026-10-04T14:35:37Z",
      "revision": 1,
      "metadata_sha256": "0ac0217cf5d0bccf21ae5fbeb20e0a66c2711c241fd03620bd7ac51a96025d68",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05200",
      "published": "2026-10-04T13:13:18Z",
      "updated": "2026-10-04T13:13:18Z",
      "revision": 1,
      "metadata_sha256": "fa8d46605f4692495f1ac1b5673f90ab4e029571a580d93094e7ae152191c9be",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "policy-llm-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05139",
      "published": "2026-10-04T11:39:57Z",
      "updated": "2026-10-04T11:39:57Z",
      "revision": 1,
      "metadata_sha256": "bd4d2fdee4ac1ff3426af41923dce6f78490cb9e702ae79872d94bfbf0d168ff",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05125",
      "published": "2026-10-04T11:13:21Z",
      "updated": "2026-10-04T11:13:21Z",
      "revision": 1,
      "metadata_sha256": "87af7172c6d4e32cbeea3ed4423be20c96356da9230d91d77ec5e73f6a7b1b4c",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.05099",
      "published": "2026-10-04T10:13:41Z",
      "updated": "2026-10-04T10:13:41Z",
      "revision": 1,
      "metadata_sha256": "29176a92d1e05bc824c6f6166f86c1c3af8f62efc89350e313d25fc3fe67b2f0",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.05097",
      "published": "2026-10-04T10:00:49Z",
      "updated": "2026-10-04T10:00:49Z",
      "revision": 1,
      "metadata_sha256": "4541418691a7adf6a0345cfcb1e87a4a3a51055f8e1c44ea1042caabb33e452c",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.05077",
      "published": "2026-10-04T09:22:10Z",
      "updated": "2026-10-04T09:22:10Z",
      "revision": 1,
      "metadata_sha256": "2f7e7dc2e38579f6af052a080ad4919c3749f3dd593758b6df2a8e6a4b11781b",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.05070",
      "published": "2026-10-04T09:13:27Z",
      "updated": "2026-10-04T09:13:27Z",
      "revision": 1,
      "metadata_sha256": "4149fac094d3fc6389e917597b45737ddcdde5f4be3f937d9df92c154c182755",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06993",
      "published": "2026-10-04T07:42:11Z",
      "updated": "2026-10-04T07:42:11Z",
      "revision": 1,
      "metadata_sha256": "6586f39676f43f4da114d03fda2248554f4770d087d8e010a755344617fea851",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04950",
      "published": "2026-10-04T04:49:24Z",
      "updated": "2026-10-04T04:49:24Z",
      "revision": 1,
      "metadata_sha256": "7f75766d0781288b55fdb9709a797ad26f6b0f94f3396119544d3d2120d8d814",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.04928",
      "published": "2026-10-04T04:13:20Z",
      "updated": "2026-10-04T04:13:20Z",
      "revision": 1,
      "metadata_sha256": "b1d06a9f6bbf1f44caaceb46cc5bdd7daef086a13f6d9802f51664584dc3f7ff",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04918",
      "published": "2026-10-04T03:56:38Z",
      "updated": "2026-10-04T03:56:38Z",
      "revision": 1,
      "metadata_sha256": "e3d94f172190b5eed82cca4b2fd56d2ce2a90f35ee291e8b24b5dba608c75bcb",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04914",
      "published": "2026-10-04T03:49:36Z",
      "updated": "2026-10-04T03:49:36Z",
      "revision": 1,
      "metadata_sha256": "51c5af05fc284c64db05c7e05b4d072b723f348061ece220af3ee406f0bada6d",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.04899",
      "published": "2026-10-04T03:19:46Z",
      "updated": "2026-10-04T03:19:46Z",
      "revision": 1,
      "metadata_sha256": "bf3333880bd3792b36bbac63373f23a6ef23243a76cd58692b0df6ac396f2a1c",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.04888",
      "published": "2026-10-04T02:53:23Z",
      "updated": "2026-10-04T02:53:23Z",
      "revision": 1,
      "metadata_sha256": "075d4765395ee1afa5ab725feeda153838d7a3ec16137782b9a020e4aa68412b",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.04882",
      "published": "2026-10-04T02:43:39Z",
      "updated": "2026-10-04T02:43:39Z",
      "revision": 1,
      "metadata_sha256": "79af04f83e24add3d57a52025d10bf0068e46d37df437bce47a571d88dc0f2e1",
      "repository_status": "reviewed",
      "matched_queries": [
        "opd",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04851",
      "published": "2026-10-04T01:30:47Z",
      "updated": "2026-10-04T01:30:47Z",
      "revision": 1,
      "metadata_sha256": "f76245de8237c48f2601fea90e8484a347c1e187013678ad2c9ccf9d1433c66e",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.04845",
      "published": "2026-10-04T01:09:45Z",
      "updated": "2026-10-04T01:09:45Z",
      "revision": 1,
      "metadata_sha256": "c8449f1c6866251a4f464a9488461f7ac8965d0853081c4ced08a3558c29e698",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "post-training",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.04754",
      "published": "2026-10-03T20:43:47Z",
      "updated": "2026-10-03T20:43:47Z",
      "revision": 1,
      "metadata_sha256": "758923081bf7d082e6beff4023c75199554a881f3eb7f97eed78c64fedb3bb20",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.06962",
      "published": "2026-10-03T17:01:42Z",
      "updated": "2026-10-03T17:01:42Z",
      "revision": 1,
      "metadata_sha256": "b2fa3076aa7fa54ec7e4b44ee0fcab5f75f8caf69133c3cfa2c5a4804c95f49c",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.04651",
      "published": "2026-10-03T16:49:17Z",
      "updated": "2026-10-03T16:49:17Z",
      "revision": 1,
      "metadata_sha256": "bc00d5bd5caea60cc1fb2cdff9376268f2c54560b1b99f78cb2e079865b8c620",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.04638",
      "published": "2026-10-03T16:29:39Z",
      "updated": "2026-10-03T16:29:39Z",
      "revision": 1,
      "metadata_sha256": "4a66db34eea6c134409df8a4460af252ba26e3dd0497fb05a4b2ca8ad4b2f37a",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04620",
      "published": "2026-10-03T16:09:37Z",
      "updated": "2026-10-03T16:09:37Z",
      "revision": 1,
      "metadata_sha256": "e63ae3daa8fdef9268c811fadc7a960a316a80ac3be5052a1fb205ac03ff317c",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04604",
      "published": "2026-10-03T15:45:17Z",
      "updated": "2026-10-03T15:45:17Z",
      "revision": 1,
      "metadata_sha256": "c759e0fafe75e447ba3cdc6d1326040b68475aaca88a90447f5e12ab3021232d",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.04596",
      "published": "2026-10-03T15:33:21Z",
      "updated": "2026-10-03T15:33:21Z",
      "revision": 1,
      "metadata_sha256": "26f0a85a3acea85a25b252b0489ae0a4139b62746834f97cce32006752e1d449",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04537",
      "published": "2026-10-03T14:07:04Z",
      "updated": "2026-10-03T14:07:04Z",
      "revision": 1,
      "metadata_sha256": "441c77179ba41b4b80997b3444f83b6017b7873e07c25f9f9dd69d25e2bdb6c8",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04507",
      "published": "2026-10-03T13:10:37Z",
      "updated": "2026-10-03T13:10:37Z",
      "revision": 1,
      "metadata_sha256": "f32278a984f539b4c1f41c3bb026ad01b7a952800c29fcd805508331e81b582c",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.06950",
      "published": "2026-10-03T12:57:57Z",
      "updated": "2026-10-08T12:50:52Z",
      "revision": 2,
      "metadata_sha256": "ebcf34fe7357ec984c9008913c53884a363416369a331899dac8b6b83472c25c",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.04441",
      "published": "2026-10-03T11:03:16Z",
      "updated": "2026-10-03T11:03:16Z",
      "revision": 1,
      "metadata_sha256": "db47ece634b275909e79d62a19a220e270ed8377e7d13d218af8c67aa59f2ac0",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.06947",
      "published": "2026-10-03T10:57:37Z",
      "updated": "2026-10-03T10:57:37Z",
      "revision": 1,
      "metadata_sha256": "9a7f0a3350f620ffce6953d341eb8137b87b2eb65104aa032b6f2ba8d82b6e75",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.04412",
      "published": "2026-10-03T10:02:14Z",
      "updated": "2026-10-03T10:02:14Z",
      "revision": 1,
      "metadata_sha256": "2a0eb1875fcec7d0e1069f0cad04a1a2c2b904da6785b450af6da8ffab230821",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04403",
      "published": "2026-10-03T09:50:16Z",
      "updated": "2026-10-03T09:50:16Z",
      "revision": 1,
      "metadata_sha256": "aaaf928d09a98df98caa8bd673ae44a163ad8e762df299e19a6e934c219dd5cd",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.04364",
      "published": "2026-10-03T08:02:22Z",
      "updated": "2026-10-03T08:02:22Z",
      "revision": 1,
      "metadata_sha256": "6f82ebfdfcff023f9961325411a5ea7a1f99f2b38be00176b08d1dcaa7777f58",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04344",
      "published": "2026-10-03T07:11:02Z",
      "updated": "2026-10-03T07:11:02Z",
      "revision": 1,
      "metadata_sha256": "37fcdd4095ad8a7f83ef242574ac8568ff37c356902baa32e05d7a02a7ff2333",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04328",
      "published": "2026-10-03T06:48:35Z",
      "updated": "2026-10-03T06:48:35Z",
      "revision": 1,
      "metadata_sha256": "683019663285bcf7d66d63d0557042365f216446bf903a054ac2cc1e05ef09c9",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.04299",
      "published": "2026-10-03T05:24:47Z",
      "updated": "2026-10-06T21:32:46Z",
      "revision": 2,
      "metadata_sha256": "73b0747a97533b087efee715c5a164ccd83cf38db8bedbb95fa1b3ff84df7dbd",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.04272",
      "published": "2026-10-03T03:57:33Z",
      "updated": "2026-10-03T03:57:33Z",
      "revision": 1,
      "metadata_sha256": "b5ea3b157879124a14d1899607755c5951b735402575ea08d56361e7d1383916",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.04269",
      "published": "2026-10-03T03:45:44Z",
      "updated": "2026-10-03T03:45:44Z",
      "revision": 1,
      "metadata_sha256": "ddd85ab4c4e82442f7b1f0b219e44bdbe1a97e5e0e2eeac4fefeeeef0867edcf",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.04261",
      "published": "2026-10-03T03:37:15Z",
      "updated": "2026-10-03T03:37:15Z",
      "revision": 1,
      "metadata_sha256": "9450441d2c42b85acea02088323343edce4c3d0beba6e12098739f3c46eddfb8",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.04158",
      "published": "2026-10-03T00:01:36Z",
      "updated": "2026-10-03T00:01:36Z",
      "revision": 1,
      "metadata_sha256": "eead152cd3c7ac15401cb7c29d13589c461d792f0b1183a70bdb6d38115ff757",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04137",
      "published": "2026-10-02T23:18:55Z",
      "updated": "2026-10-02T23:18:55Z",
      "revision": 1,
      "metadata_sha256": "ba938c7fa3e41849bfeb5384608776bd92f188a9e6a17e9a77506ff0c27f8f50",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04134",
      "published": "2026-10-02T23:08:20Z",
      "updated": "2026-10-02T23:08:20Z",
      "revision": 1,
      "metadata_sha256": "8f0d7bd7e8ebdbcc1986e5dd99f18e7dac1bfae1d35c6530d65758b01795fa81",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04132",
      "published": "2026-10-02T23:07:24Z",
      "updated": "2026-10-02T23:07:24Z",
      "revision": 1,
      "metadata_sha256": "702ced6a1b3422273eef354ce4d0c229cbb361d9cd8cedfdb4eee525c5c4b778",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "preference-optimization",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.04089",
      "published": "2026-10-02T21:54:46Z",
      "updated": "2026-10-02T21:54:46Z",
      "revision": 1,
      "metadata_sha256": "6a2c71c780b4ddc08e4f43ffa48936cf391f04cc5cc056949c037d4147a3676d",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03984",
      "published": "2026-10-02T19:47:19Z",
      "updated": "2026-10-02T19:47:19Z",
      "revision": 1,
      "metadata_sha256": "aead8a6ed5b99da2abf6f56740ddd37cbbbea8127e27df3acf67a1494f30cdeb",
      "repository_status": "reviewed",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.03972",
      "published": "2026-10-02T19:30:02Z",
      "updated": "2026-10-02T19:30:02Z",
      "revision": 1,
      "metadata_sha256": "245af58a4a881cbde818504ba59f245cc4b83a7d833872cbc757cf1619f6c961",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.03880",
      "published": "2026-10-02T18:02:02Z",
      "updated": "2026-10-02T18:02:02Z",
      "revision": 1,
      "metadata_sha256": "86c8e835f2b37ff5218e719943dc19b99cfc30f167e680f18900c2d8d23bfe4a",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03709",
      "published": "2026-10-02T17:57:50Z",
      "updated": "2026-10-14T02:44:11Z",
      "revision": 2,
      "metadata_sha256": "8d5272e0fa99f73e43afee0ea3b8c0d6cc0f52422bdb7ea8a824671b553c5563",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.03702",
      "published": "2026-10-02T17:55:42Z",
      "updated": "2026-10-02T17:55:42Z",
      "revision": 1,
      "metadata_sha256": "bbcc5725a71d3801049d7590294b72895d2501762d6a05c2f706bb79e71c5bb3",
      "repository_status": "implemented",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.03667",
      "published": "2026-10-02T17:38:28Z",
      "updated": "2026-10-02T17:38:28Z",
      "revision": 1,
      "metadata_sha256": "b200fc0eac42b12f466070c86a812d97dd39284081a33e0eada4cbdc998b01c1",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03665",
      "published": "2026-10-02T17:37:51Z",
      "updated": "2026-10-02T17:37:51Z",
      "revision": 1,
      "metadata_sha256": "11630b57d7f41f75b759922234eb00f64e92ba91c5df1a127e51ddce0e7c0b83",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.03585",
      "published": "2026-10-02T16:55:50Z",
      "updated": "2026-10-02T16:55:50Z",
      "revision": 1,
      "metadata_sha256": "0b40eb16a968055ef27bf0b3cfdad1acfffe6889db8e35e89ce6ea10d94d02cb",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03567",
      "published": "2026-10-02T16:44:53Z",
      "updated": "2026-10-02T16:44:53Z",
      "revision": 1,
      "metadata_sha256": "05f7f7fe8935aec08b85c94ce1f3bcd76483942814a507d7f6806aa7c519ff95",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.03529",
      "published": "2026-10-02T16:15:53Z",
      "updated": "2026-10-02T16:15:53Z",
      "revision": 1,
      "metadata_sha256": "0ebaa06bee31ae25dcfa22fa57d26e9236dceb5c4bb3a02d4e9a817adb9c1a61",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.03515",
      "published": "2026-10-02T16:07:39Z",
      "updated": "2026-10-02T16:07:39Z",
      "revision": 1,
      "metadata_sha256": "6ddc109f81112ba0e2619d7c0c88b8ba5ecda449314de5e0e636844fbff33014",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03480",
      "published": "2026-10-02T15:49:38Z",
      "updated": "2026-10-02T15:49:38Z",
      "revision": 1,
      "metadata_sha256": "dec02e17034352866b56ec606f75cf5541bb69e2c8a35bdfcb490ce0e5a9f199",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.03458",
      "published": "2026-10-02T15:33:56Z",
      "updated": "2026-10-02T15:33:56Z",
      "revision": 1,
      "metadata_sha256": "57941c5a2e6d8a3415f5f33d5fc321438e5774f6657d238c95b925e7c5aedf70",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03454",
      "published": "2026-10-02T15:33:07Z",
      "updated": "2026-10-02T15:33:07Z",
      "revision": 1,
      "metadata_sha256": "f4af163c8e5fc2f23adf7ed396e77973b02bd66fcf473308ba09101d0f5ca3db",
      "repository_status": "reviewed",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.03369",
      "published": "2026-10-02T14:27:26Z",
      "updated": "2026-10-13T07:19:27Z",
      "revision": 2,
      "metadata_sha256": "bbe72cb5e3cb31e98add1c28195f900b4109f64821d15251e8356bc46f8d8099",
      "repository_status": "reviewed",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.03361",
      "published": "2026-10-02T14:24:06Z",
      "updated": "2026-10-02T14:24:06Z",
      "revision": 1,
      "metadata_sha256": "540d4d18fcd8420bc8660c07f9685a5a4cdeaa233e53d94b2b6a7216e9f330ae",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03225",
      "published": "2026-10-02T12:41:43Z",
      "updated": "2026-10-14T16:14:37Z",
      "revision": 2,
      "metadata_sha256": "fe8f2f49ebc7d695c05392a3b10cebbcb986995f586aa52d9b14cf7b887db315",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.03223",
      "published": "2026-10-02T12:38:53Z",
      "updated": "2026-10-11T15:19:02Z",
      "revision": 2,
      "metadata_sha256": "da9fa27f9f7e4c434ef1a04e727317c39f3f978aad00527ca590abc616005222",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.03201",
      "published": "2026-10-02T12:16:27Z",
      "updated": "2026-10-14T13:36:30Z",
      "revision": 2,
      "metadata_sha256": "18055d705ae8bfde9cb8e747006967fa7a2861edd82b8fddc4bd5b841c9938ee",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.03195",
      "published": "2026-10-02T12:10:03Z",
      "updated": "2026-10-02T12:10:03Z",
      "revision": 1,
      "metadata_sha256": "2d6b5462f8006ea3e8e9591d32a4c2bf6a95f865f74a3323ab254e7686df2e98",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.03190",
      "published": "2026-10-02T12:06:02Z",
      "updated": "2026-10-02T12:06:02Z",
      "revision": 1,
      "metadata_sha256": "de6f6b976d8513a6f7adb011bc69864f0889cec5de1939e8da2d04f5169f913a",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03185",
      "published": "2026-10-02T11:57:36Z",
      "updated": "2026-10-02T11:57:36Z",
      "revision": 1,
      "metadata_sha256": "55e3bf738ae7ec197b92fc558446dcd600e17b248696b41af270e20f8656dc7b",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.03109",
      "published": "2026-10-02T10:27:59Z",
      "updated": "2026-10-02T10:27:59Z",
      "revision": 1,
      "metadata_sha256": "570286d46eb5ee55ddf73c571bb347a149f5d3505c97578ca54be3b21b3f5a51",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.03063",
      "published": "2026-10-02T09:46:40Z",
      "updated": "2026-10-02T09:46:40Z",
      "revision": 1,
      "metadata_sha256": "c51911a7487b60dd696c24792c4fe010040d36b0b7be24a45d49399a614b2b25",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.03025",
      "published": "2026-10-02T09:01:07Z",
      "updated": "2026-10-06T02:20:51Z",
      "revision": 2,
      "metadata_sha256": "7e07e171507c8b3470a99e55ce6951013c25200f4d80bd58b3387bbfe1a17dd5",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02986",
      "published": "2026-10-02T08:22:46Z",
      "updated": "2026-10-02T08:22:46Z",
      "revision": 1,
      "metadata_sha256": "44e6a99c6d59a8dfacb7441dbe975b3cc82a13f178e954464763b48a95aa6b77",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.02911",
      "published": "2026-10-02T07:02:13Z",
      "updated": "2026-10-02T07:02:13Z",
      "revision": 1,
      "metadata_sha256": "cf4f2d2f038b05ac0294a955f3e5262970a7b9240a81ca69aa0edcb3b9e9d5b9",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02886",
      "published": "2026-10-02T06:24:54Z",
      "updated": "2026-10-02T06:24:54Z",
      "revision": 1,
      "metadata_sha256": "a1399b3de5ccffc2a8244a675e341801881aff04966919d3ed29545bd9b0d827",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.02856",
      "published": "2026-10-02T05:42:22Z",
      "updated": "2026-10-02T05:42:22Z",
      "revision": 1,
      "metadata_sha256": "a98d8e470c6796d5f507aace514dad0a476d7291b74c46681a28b722f80acac5",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.02848",
      "published": "2026-10-02T05:35:53Z",
      "updated": "2026-10-02T05:35:53Z",
      "revision": 1,
      "metadata_sha256": "5e549d58597e298e7f396f89374adc9eea690ab5f3aa25056cec8df72c9b0897",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02846",
      "published": "2026-10-02T05:34:41Z",
      "updated": "2026-10-02T05:34:41Z",
      "revision": 1,
      "metadata_sha256": "897bf385e55db09bfff788d0f1f44ddbed1ddb780752e9d389814bd03016a669",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02835",
      "published": "2026-10-02T05:27:33Z",
      "updated": "2026-10-02T05:27:33Z",
      "revision": 1,
      "metadata_sha256": "53824f1f6a8132e3af3f4db27562d2e077daea26cfed919d54e5db5583174e02",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02832",
      "published": "2026-10-02T05:24:20Z",
      "updated": "2026-10-02T05:24:20Z",
      "revision": 1,
      "metadata_sha256": "b21a704a9733d1646edcd759e3ccf4170bc667a67be621467f7698bd37a5b359",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.02828",
      "published": "2026-10-02T05:19:54Z",
      "updated": "2026-10-02T05:19:54Z",
      "revision": 1,
      "metadata_sha256": "f194532cf9a8f9537247cbda082b0686abadab45f4b73e96644da2ca6ff94d23",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02819",
      "published": "2026-10-02T05:08:25Z",
      "updated": "2026-10-02T05:08:25Z",
      "revision": 1,
      "metadata_sha256": "0a387e79f1c5d74b3e1318e2050e79f1f9f3ee6c7f7bdd56cfb17473847c93b9",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.02808",
      "published": "2026-10-02T04:59:24Z",
      "updated": "2026-10-02T04:59:24Z",
      "revision": 1,
      "metadata_sha256": "41e08ab5a79d9abd7cc27047b045574f6f9e6a465659d63931a69e85cb771799",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02795",
      "published": "2026-10-02T04:35:59Z",
      "updated": "2026-10-14T06:54:18Z",
      "revision": 2,
      "metadata_sha256": "27b0c6c307a1edde592b6482e22b4f90999c5a41f3e66660b3ab4662b3e286bb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.02781",
      "published": "2026-10-02T04:14:57Z",
      "updated": "2026-10-02T04:14:57Z",
      "revision": 1,
      "metadata_sha256": "71713350813b028b58707ea17dd4a982f3550d448065a81c240740ecfedeb51a",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02766",
      "published": "2026-10-02T03:47:10Z",
      "updated": "2026-10-02T03:47:10Z",
      "revision": 1,
      "metadata_sha256": "07a2b39c9d228e25efb7b7f2aaca880060dbc266db74837672b49757f23e5deb",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02744",
      "published": "2026-10-02T03:16:28Z",
      "updated": "2026-10-02T03:16:28Z",
      "revision": 1,
      "metadata_sha256": "6813cb0c84a836b90265eff3366807045de86fe9caf72050196a6f437c304c7b",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02740",
      "published": "2026-10-02T03:12:00Z",
      "updated": "2026-10-02T03:12:00Z",
      "revision": 1,
      "metadata_sha256": "2e7b64543578b0fa9d65edb640a299c3883b81aec9f7ee4ae1e64dc06d37631c",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02700",
      "published": "2026-10-02T02:34:57Z",
      "updated": "2026-10-02T02:34:57Z",
      "revision": 1,
      "metadata_sha256": "6580d62d1bd5f528aacbdaa1131c6240ebfc19cb9f9785764e0f47b394e7cb66",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02695",
      "published": "2026-10-02T02:17:17Z",
      "updated": "2026-10-02T02:17:17Z",
      "revision": 1,
      "metadata_sha256": "9dc9835e7a79baf904d0f81b9c06a04f77aced4512785e644c4807c1a1e40594",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.02626",
      "published": "2026-10-02T00:31:51Z",
      "updated": "2026-10-13T20:07:42Z",
      "revision": 3,
      "metadata_sha256": "6fbe9d2ffed014bd58d30ea6258d81f183b1828c469f8de852130b5b2edf3d85",
      "repository_status": "reviewed",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.02614",
      "published": "2026-10-02T00:14:40Z",
      "updated": "2026-10-02T00:14:40Z",
      "revision": 1,
      "metadata_sha256": "66f8b97eed0c31d9d34ed17a3c5c246f5c171fdf8ed799a31b71ee8949ee681d",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02593",
      "published": "2026-10-01T23:44:09Z",
      "updated": "2026-10-01T23:44:09Z",
      "revision": 1,
      "metadata_sha256": "4ddc2c3c3f87babc70620143bc6687aaab8299608ffab596e17572f7d2bd261e",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.02554",
      "published": "2026-10-01T22:38:27Z",
      "updated": "2026-10-01T22:38:27Z",
      "revision": 1,
      "metadata_sha256": "5d4dff48f16a51cce635dea69ff147a8a9acb2de95c3a33bc3741b12fab2e224",
      "repository_status": "reviewed",
      "matched_queries": [
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.02505",
      "published": "2026-10-01T21:27:02Z",
      "updated": "2026-10-01T21:27:02Z",
      "revision": 1,
      "metadata_sha256": "05aef7e42ac7f99b6785a7014c676767847eb9b23f76e790716916cb962b2a7c",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02488",
      "published": "2026-10-01T21:05:49Z",
      "updated": "2026-10-06T18:59:26Z",
      "revision": 2,
      "metadata_sha256": "c1dadee4e4513751f6b855f9efd497280b403d24ca00dd3796422dddec3058de",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02486",
      "published": "2026-10-01T21:03:42Z",
      "updated": "2026-10-01T21:03:42Z",
      "revision": 1,
      "metadata_sha256": "78ed2875e7d87407409faf919ff791e5859024abf833802d9d39334d5f7b43ee",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02466",
      "published": "2026-10-01T20:40:29Z",
      "updated": "2026-10-01T20:40:29Z",
      "revision": 1,
      "metadata_sha256": "c8c630f3a3b602574d24272b26304fe34f3e54484b5f35f35281c26099cfcfed",
      "repository_status": "reviewed",
      "matched_queries": [
        "opd"
      ]
    },
    {
      "arxiv_id": "2610.02444",
      "published": "2026-10-01T20:13:14Z",
      "updated": "2026-10-01T20:13:14Z",
      "revision": 1,
      "metadata_sha256": "29e02b45ac644d43003a77aa650b60530ff48e73d21f7c226a06e78a7ee5e315",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02438",
      "published": "2026-10-01T20:04:14Z",
      "updated": "2026-10-01T20:04:14Z",
      "revision": 1,
      "metadata_sha256": "c10100a0a693b7d0f1892733f3614bbee4bfb9dd57f09588677c3fcb1de5b884",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.18883",
      "published": "2026-10-01T20:01:20Z",
      "updated": "2026-10-01T20:01:20Z",
      "revision": 1,
      "metadata_sha256": "b830af9574069d7fdb60ba06114f2d78d639a3a1c584905ef7d70ef676688959",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02381",
      "published": "2026-10-01T19:01:56Z",
      "updated": "2026-10-01T19:01:56Z",
      "revision": 1,
      "metadata_sha256": "6bee0595955acb40bb3cf513bec6be6015086377d116d0a621d0db03a4a53393",
      "repository_status": "new",
      "matched_queries": [
        "opd-abbreviation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02359",
      "published": "2026-10-01T18:35:35Z",
      "updated": "2026-10-01T18:35:35Z",
      "revision": 1,
      "metadata_sha256": "eb6f78676b15a7aee512b3e33e11022be456c78134fa0803611f769582e1774d",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02351",
      "published": "2026-10-01T18:25:07Z",
      "updated": "2026-10-01T18:25:07Z",
      "revision": 1,
      "metadata_sha256": "cf403320bcfdb9ae9f45b337e220dd1e16261ccf7dc99514958592c698a38fdc",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.02324",
      "published": "2026-10-01T18:00:27Z",
      "updated": "2026-10-01T18:00:27Z",
      "revision": 1,
      "metadata_sha256": "d67617f45b5455c58c0c11ac038b36390b1a7328a9b76dfbadb5454ca2d1b591",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.02206",
      "published": "2026-10-01T17:59:55Z",
      "updated": "2026-10-01T17:59:55Z",
      "revision": 1,
      "metadata_sha256": "e02f84b1d16e450235ede406117e614a5442b389752db6688e1f1c4d61f6dea6",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02191",
      "published": "2026-10-01T17:59:32Z",
      "updated": "2026-10-01T17:59:32Z",
      "revision": 1,
      "metadata_sha256": "f2395e79e8b2e116f0d31ff905bd2e81acb666e735a9bcf0d327cc7697015a12",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.02190",
      "published": "2026-10-01T17:59:28Z",
      "updated": "2026-10-01T17:59:28Z",
      "revision": 1,
      "metadata_sha256": "7140ea094ce6eee3edbe58a0e1ed0598e8ad98d7d062311c697842d7b813e2f1",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.02189",
      "published": "2026-10-01T17:59:20Z",
      "updated": "2026-10-01T17:59:20Z",
      "revision": 1,
      "metadata_sha256": "6b9f599de0f6349ac55eeb7f64ed130679e8e7b6904155bc995438405e8d083c",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02173",
      "published": "2026-10-01T17:57:04Z",
      "updated": "2026-10-01T17:57:04Z",
      "revision": 1,
      "metadata_sha256": "a780074a06b755d847dc18f85fdbb419f01eb4d20029c685e11a76e58786d9a9",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.02163",
      "published": "2026-10-01T17:54:34Z",
      "updated": "2026-10-01T17:54:34Z",
      "revision": 1,
      "metadata_sha256": "418f4fbc11a8476b13d29cde0c2fa7c5356258be27fa65212842922d00551663",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02140",
      "published": "2026-10-01T17:45:07Z",
      "updated": "2026-10-01T17:45:07Z",
      "revision": 1,
      "metadata_sha256": "e5146a06f5ed65d6d93c3c43f6b7470aafeb7a8236b2434233dc2f0e76c6c1cb",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.02117",
      "published": "2026-10-01T17:34:10Z",
      "updated": "2026-10-01T17:34:10Z",
      "revision": 1,
      "metadata_sha256": "8c61f2cda36ef2d8cb4e3986356b470f577cf064af1dee452fe4cb524a4fed7c",
      "repository_status": "implemented",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.02098",
      "published": "2026-10-01T17:25:23Z",
      "updated": "2026-10-10T03:05:46Z",
      "revision": 2,
      "metadata_sha256": "107dd25479d6f7c0db662ef6d7b1b67cc82180ae7026f9e225e55685ad42173b",
      "repository_status": "new",
      "matched_queries": [
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02039",
      "published": "2026-10-01T16:51:56Z",
      "updated": "2026-10-01T16:51:56Z",
      "revision": 1,
      "metadata_sha256": "d30edda1b1a005e478d941a483a82c6ebd95b51e3def9752d0800a23bb4d05a7",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.02019",
      "published": "2026-10-01T16:42:30Z",
      "updated": "2026-10-01T16:42:30Z",
      "revision": 1,
      "metadata_sha256": "fd4679cfe4f2e05018d5e9174344014ed7521895c0a113dadb4fc12b9d0749c0",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.02015",
      "published": "2026-10-01T16:39:48Z",
      "updated": "2026-10-01T16:39:48Z",
      "revision": 1,
      "metadata_sha256": "daa8036dfa9dbd94807adb9e1357a6a293de541edf4f525ea83c017df7770417",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01984",
      "published": "2026-10-01T16:26:10Z",
      "updated": "2026-10-02T15:53:55Z",
      "revision": 2,
      "metadata_sha256": "b634ed894573d0816f7ee4a2086be9fbd0976ad80ad6f3347f022258475e1430",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01955",
      "published": "2026-10-01T16:12:58Z",
      "updated": "2026-10-01T16:12:58Z",
      "revision": 1,
      "metadata_sha256": "53dcaee4a44c3b0acf91c4a0dad5fae74f679efaaa0dc51ec6d24346f9b98568",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.01908",
      "published": "2026-10-01T15:53:22Z",
      "updated": "2026-10-01T15:53:22Z",
      "revision": 1,
      "metadata_sha256": "f36357066c44f809ac511217c8bfd878e673cc975a47ebfae12eb0c18fa99282",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01896",
      "published": "2026-10-01T15:45:08Z",
      "updated": "2026-10-01T15:45:08Z",
      "revision": 1,
      "metadata_sha256": "dc9cc0632016e1e696c9e506ef21202b8e2cb453003d48d3a3b6da95c0516ff4",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "post-training",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01892",
      "published": "2026-10-01T15:42:14Z",
      "updated": "2026-10-08T22:17:18Z",
      "revision": 2,
      "metadata_sha256": "28a17ba97e98c2c6166c0a58cedb39efb7e498ee62128a3ce750ab838aa9c023",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2610.01828",
      "published": "2026-10-01T15:04:05Z",
      "updated": "2026-10-01T15:04:05Z",
      "revision": 1,
      "metadata_sha256": "b15da75a1e7ecae7a81b410ada8a98f2a3585365413855001bb2814570d2352a",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.01821",
      "published": "2026-10-01T14:55:03Z",
      "updated": "2026-10-01T14:55:03Z",
      "revision": 1,
      "metadata_sha256": "fdf7bb42d270e275de2b53501c79aaa5b49d8ad8d950c0ae996488efd14d5feb",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01815",
      "published": "2026-10-01T14:51:03Z",
      "updated": "2026-10-01T14:51:03Z",
      "revision": 1,
      "metadata_sha256": "202e710387aeb749100954864d3b043f93441bc3dd8699e31b31dfdb81fa9598",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.01738",
      "published": "2026-10-01T14:10:36Z",
      "updated": "2026-10-14T11:25:52Z",
      "revision": 2,
      "metadata_sha256": "45714295c43dbf38c4d39de78ab3f69233c8cf1ad617a6fad24f737d41291ca3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.01729",
      "published": "2026-10-01T14:02:24Z",
      "updated": "2026-10-01T14:02:24Z",
      "revision": 1,
      "metadata_sha256": "ac497e112a8a98a5c8ea0cb6b7d33d59c00cd36b196233365d829f54acee5bb8",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01670",
      "published": "2026-10-01T13:30:07Z",
      "updated": "2026-10-01T13:30:07Z",
      "revision": 1,
      "metadata_sha256": "01c85f4eb8b89c2bbaf232a493f0b12db08d9e51cb267159157231b9cd3cedb5",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.01652",
      "published": "2026-10-01T13:15:42Z",
      "updated": "2026-10-01T13:15:42Z",
      "revision": 1,
      "metadata_sha256": "015ca4b7b35d6dcc76c76d1bd7a289ca87ca8da22ad19cded4aa98e24a969e8d",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01560",
      "published": "2026-10-01T12:28:03Z",
      "updated": "2026-10-01T12:28:03Z",
      "revision": 1,
      "metadata_sha256": "1c491092c3ef48ebc1832385b467182beb83aee0a6dce679cbe5cd5ce492a986",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.01548",
      "published": "2026-10-01T12:16:34Z",
      "updated": "2026-10-02T03:04:07Z",
      "revision": 2,
      "metadata_sha256": "c19bc2b5d478cb3e522e950611f6145db1018b29378a5af3a51e518a78da0309",
      "repository_status": "implemented",
      "matched_queries": [
        "policy-llm-abbreviation",
        "post-training",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01513",
      "published": "2026-10-01T11:48:32Z",
      "updated": "2026-10-01T11:48:32Z",
      "revision": 1,
      "metadata_sha256": "a2548e0a243a0b983f1ec664bae8c33d6e5485b3da3d97e9aa08da4052b71b68",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.01511",
      "published": "2026-10-01T11:46:28Z",
      "updated": "2026-10-02T08:02:08Z",
      "revision": 2,
      "metadata_sha256": "f3084e618df6574a980ab8ef540cc70911a542150659857bb84d4a23a33d92bc",
      "repository_status": "implemented",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.01509",
      "published": "2026-10-01T11:46:00Z",
      "updated": "2026-10-01T11:46:00Z",
      "revision": 1,
      "metadata_sha256": "7e53b9f7663f8344c013c373614b308545083d27a368fa5e619a50bb5a4608f7",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.01399",
      "published": "2026-10-01T10:05:35Z",
      "updated": "2026-10-01T10:05:35Z",
      "revision": 1,
      "metadata_sha256": "4aaff7be72763a1cf4428b921660a36739918b5b60815af0a82338b2b35183e6",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01345",
      "published": "2026-10-01T09:17:22Z",
      "updated": "2026-10-01T09:17:22Z",
      "revision": 1,
      "metadata_sha256": "fda7c79db815d075d998325ff95710a7f25038fcf926fb5965a9860e081c06da",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01278",
      "published": "2026-10-01T08:16:07Z",
      "updated": "2026-10-01T08:16:07Z",
      "revision": 1,
      "metadata_sha256": "65cf5246eeb6d3473f8282fda9efec8fd9eae814e19f2712669873757a077162",
      "repository_status": "reviewed",
      "matched_queries": [
        "on-policy-distillation"
      ]
    },
    {
      "arxiv_id": "2610.01275",
      "published": "2026-10-01T08:13:50Z",
      "updated": "2026-10-01T08:13:50Z",
      "revision": 1,
      "metadata_sha256": "accbed213a7ced7ffda768da870a282b36e18398ca5365199f1c18d5b4405ec7",
      "repository_status": "reviewed",
      "matched_queries": [
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.01238",
      "published": "2026-10-01T07:37:37Z",
      "updated": "2026-10-01T07:37:37Z",
      "revision": 1,
      "metadata_sha256": "f323ab27c92773744222a6f13fd78250aa49a9c959e4bc719a01ed9a093236c0",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.01234",
      "published": "2026-10-01T07:35:30Z",
      "updated": "2026-10-01T07:35:30Z",
      "revision": 1,
      "metadata_sha256": "db262704d710d0544d79e059c1209e2965e5995e73c1b308d1255749c79fe000",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01161",
      "published": "2026-10-01T06:41:10Z",
      "updated": "2026-10-01T06:41:10Z",
      "revision": 1,
      "metadata_sha256": "63300248a4e5279e0559552293fe89f6c7ce595bdf92480605c4e4376761facf",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01128",
      "published": "2026-10-01T06:11:48Z",
      "updated": "2026-10-01T06:11:48Z",
      "revision": 1,
      "metadata_sha256": "d7408b460a10aac83941f1e3f0015689ff0ca7b52083060b9a912356247fb996",
      "repository_status": "reviewed",
      "matched_queries": [
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.03799",
      "published": "2026-10-01T05:57:05Z",
      "updated": "2026-10-01T05:57:05Z",
      "revision": 1,
      "metadata_sha256": "0fe8d91f7e2969f0d9363987d7f25749bfc93da94b61b284c2712339a7f28b17",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01076",
      "published": "2026-10-01T05:16:20Z",
      "updated": "2026-10-01T05:16:20Z",
      "revision": 1,
      "metadata_sha256": "982c87242d781a6f57a81054a88d75f85fbdeceb0b774e826e54c83a78ce293c",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01066",
      "published": "2026-10-01T05:05:29Z",
      "updated": "2026-10-01T05:05:29Z",
      "revision": 1,
      "metadata_sha256": "b7eb2c42a2fef7d8ba4de28f7b06e9df5dcd6503db271012516322e395650bef",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.01042",
      "published": "2026-10-01T04:34:59Z",
      "updated": "2026-10-01T04:34:59Z",
      "revision": 1,
      "metadata_sha256": "d0c5b3224a8f814513d9ce34571c5501eb7a2e3d789690b32ece0152c09e58e4",
      "repository_status": "reviewed",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.01026",
      "published": "2026-10-01T04:15:49Z",
      "updated": "2026-10-01T04:15:49Z",
      "revision": 1,
      "metadata_sha256": "1b7be2e081f1d7af4e3b2d2e989e2aa28667b267f76365bdfa5d5830ba6708d0",
      "repository_status": "implemented",
      "matched_queries": [
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.00991",
      "published": "2026-10-01T03:25:40Z",
      "updated": "2026-10-02T01:56:54Z",
      "revision": 2,
      "metadata_sha256": "9b2462160d2fcec0d1a3a03e9bf64f4dda7b3b406eed10c6ba8b2f106e826661",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.00988",
      "published": "2026-10-01T03:22:43Z",
      "updated": "2026-10-01T03:22:43Z",
      "revision": 1,
      "metadata_sha256": "1ca1df5bb65310dc436ced777b501bf763aa8580f9dcccdddaa5f125bc32e577",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00983",
      "published": "2026-10-01T03:19:52Z",
      "updated": "2026-10-01T03:19:52Z",
      "revision": 1,
      "metadata_sha256": "57045bff569169da10fbc293bf9a0ea736f1022d2196ba41f4863805bfdcd723",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.18881",
      "published": "2026-10-01T03:08:52Z",
      "updated": "2026-10-01T03:08:52Z",
      "revision": 1,
      "metadata_sha256": "8cce0f3c9a81f78098b7fac2ce74ac35ed4c00074deb689510f205a2f427dc59",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00964",
      "published": "2026-10-01T02:52:24Z",
      "updated": "2026-10-02T21:04:32Z",
      "revision": 2,
      "metadata_sha256": "bd6a0043af5e01e28ba98c82e3c6b85a53d7c7f81cc9c8e69f14155e158f2813",
      "repository_status": "implemented",
      "matched_queries": [
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.00958",
      "published": "2026-10-01T02:39:52Z",
      "updated": "2026-10-10T01:41:05Z",
      "revision": 2,
      "metadata_sha256": "05c1448a899996eaef5eb30cafc997e195b39fd3b25f616b9bfe4e0aa02e2f3e",
      "repository_status": "implemented",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00954",
      "published": "2026-10-01T02:37:56Z",
      "updated": "2026-10-01T02:37:56Z",
      "revision": 1,
      "metadata_sha256": "23a70add5d51cd9b09e85c2064cee721228db660a0b5c9c424e3eb1b4a0da02e",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.18880",
      "published": "2026-10-01T02:29:02Z",
      "updated": "2026-10-01T02:29:02Z",
      "revision": 1,
      "metadata_sha256": "98ccfd44ef155e45393f8d0e94a019dad293cf94e3044d604ce69de4df69de58",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18879",
      "published": "2026-10-01T02:12:27Z",
      "updated": "2026-10-01T02:12:27Z",
      "revision": 1,
      "metadata_sha256": "8b1f43a8aba106c74bc4363841beb9f4f7e7e380848d7937a0366fbe649716fa",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.18878",
      "published": "2026-10-01T01:56:34Z",
      "updated": "2026-10-01T01:56:34Z",
      "revision": 1,
      "metadata_sha256": "5c174c8964dd4f6832a96659b140e7d6ce8673bbeeb1d5203a8617ec8587517b",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.18877",
      "published": "2026-10-01T01:44:55Z",
      "updated": "2026-10-01T01:44:55Z",
      "revision": 1,
      "metadata_sha256": "eb387650315c9c340673e5aaa554a95eef5ef28bba0790b7cd63ddb4213dd784",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.00903",
      "published": "2026-10-01T01:33:30Z",
      "updated": "2026-10-01T01:33:30Z",
      "revision": 1,
      "metadata_sha256": "4efc3381a74860d23b08a4e2f39400b161a41523b74aacc9fafe232be85c6614",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "post-training",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.00898",
      "published": "2026-10-01T01:27:31Z",
      "updated": "2026-10-01T01:27:31Z",
      "revision": 1,
      "metadata_sha256": "e3c2f54fdb3cd4d28d9e81662fda36d497d24c576abe7663ef70c4483295dbde",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00888",
      "published": "2026-10-01T01:09:18Z",
      "updated": "2026-10-01T01:09:18Z",
      "revision": 1,
      "metadata_sha256": "954f7375e52ed660277b83c725128b936ad65b10446305b88112afa0f5fb2ae8",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00852",
      "published": "2026-10-01T00:12:27Z",
      "updated": "2026-10-01T00:12:27Z",
      "revision": 1,
      "metadata_sha256": "e9572794ef6ecb733cc027a55c9b8d8a5c40a2eec411062df238ade8062b61fe",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00838",
      "published": "2026-09-30T23:51:11Z",
      "updated": "2026-10-04T03:42:50Z",
      "revision": 2,
      "metadata_sha256": "67b14475f6ad83a035db4b9109a9eef9d5ca5261aa329c00176effd3c71e05c0",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.14030",
      "published": "2026-09-30T23:32:34Z",
      "updated": "2026-09-30T23:32:34Z",
      "revision": 1,
      "metadata_sha256": "877c4c8df9099d05e05f32f2e654b023a5d3d0e3333c166e6ea1c2b44f8caee9",
      "repository_status": "new",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00779",
      "published": "2026-09-30T22:16:23Z",
      "updated": "2026-09-30T22:16:23Z",
      "revision": 1,
      "metadata_sha256": "d455993679347dfafbe50053f26b08d6366ff7527f8e960c7838dccb37e45a54",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00767",
      "published": "2026-09-30T22:02:46Z",
      "updated": "2026-09-30T22:02:46Z",
      "revision": 1,
      "metadata_sha256": "38580f038f0d3fc4a83a965b3ca4782c4ff6d7e6e713f7422802519573022dd8",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00717",
      "published": "2026-09-30T21:06:29Z",
      "updated": "2026-09-30T21:06:29Z",
      "revision": 1,
      "metadata_sha256": "839e2e0381e8ea69b0cd9288d0ccb3a3390e2b6e964bec2e80345da070f299d8",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00663",
      "published": "2026-09-30T20:02:14Z",
      "updated": "2026-09-30T20:02:14Z",
      "revision": 1,
      "metadata_sha256": "386267d3758409cc8195bc51cd9f09692e99d382fc4a1f09dc9f12af2c3e5620",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00661",
      "published": "2026-09-30T19:59:48Z",
      "updated": "2026-10-09T07:30:38Z",
      "revision": 2,
      "metadata_sha256": "5d4815c6af7d6ed20ce6d88ec862c649ae63fc162ba59afcfcfb3bdb38457446",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00610",
      "published": "2026-09-30T19:13:19Z",
      "updated": "2026-10-02T02:17:59Z",
      "revision": 2,
      "metadata_sha256": "e67bc5596af30635df4e4fe3936422e445a90e891c5006a3a0229cf073ca175b",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00592",
      "published": "2026-09-30T18:55:45Z",
      "updated": "2026-09-30T18:55:45Z",
      "revision": 1,
      "metadata_sha256": "8745be526a5d2c852cc8c07f3686c2084ce57a64142e021ed253a15f7f503858",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00574",
      "published": "2026-09-30T18:45:26Z",
      "updated": "2026-09-30T18:45:26Z",
      "revision": 1,
      "metadata_sha256": "78aeafd13d07a42a8af702d5288876cf40b8a857c778728cab0f50c8ffe04be9",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.00568",
      "published": "2026-09-30T18:41:05Z",
      "updated": "2026-09-30T18:41:05Z",
      "revision": 1,
      "metadata_sha256": "ce6f7866e7b947427fea5831582e47bdafc8dd7e65790cf04b7e9784a77d0618",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00540",
      "published": "2026-09-30T18:22:47Z",
      "updated": "2026-09-30T18:22:47Z",
      "revision": 1,
      "metadata_sha256": "a137322b36fb5f7193f1d3b2cab1c8e33008ad7e4959f0f0cae859661f66fe60",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00431",
      "published": "2026-09-30T16:43:34Z",
      "updated": "2026-09-30T16:43:34Z",
      "revision": 1,
      "metadata_sha256": "6228a0bcd5620d0499c7d44c06b8dc77d82fe029e670c01bad3e111f61493b9a",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00388",
      "published": "2026-09-30T10:34:27Z",
      "updated": "2026-09-30T10:34:27Z",
      "revision": 1,
      "metadata_sha256": "2c16c130480013f2d4d71423f7a1bb1850670d227ddad7f366c20aa2f4f1a543",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00385",
      "published": "2026-09-30T09:41:08Z",
      "updated": "2026-09-30T09:41:08Z",
      "revision": 1,
      "metadata_sha256": "527f68f6c76d9660725b1d637ec9d52c4633b4f9901d54dd04e8f0c6ee21fb69",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2610.00367",
      "published": "2026-09-30T06:38:43Z",
      "updated": "2026-09-30T06:38:43Z",
      "revision": 1,
      "metadata_sha256": "329896664ea47ec8c39305b9603cec467dd100fcc8fffbdbc26b8890009d92bb",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2610.14022",
      "published": "2026-09-29T14:07:18Z",
      "updated": "2026-09-29T14:07:18Z",
      "revision": 1,
      "metadata_sha256": "51e0c2d9f0649476168ca0656d1158564684a7f36870552b36175abbb5c94704",
      "repository_status": "new",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00333",
      "published": "2026-09-29T13:57:51Z",
      "updated": "2026-09-29T13:57:51Z",
      "revision": 1,
      "metadata_sha256": "148b3cd7e366d5830a79e0cc6ef9c422ea7ec7262c28ce020088023e265d2245",
      "repository_status": "implemented",
      "matched_queries": [
        "on-policy-distillation",
        "opd-abbreviation",
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00332",
      "published": "2026-09-29T13:51:52Z",
      "updated": "2026-09-29T13:51:52Z",
      "revision": 1,
      "metadata_sha256": "a4ee79a7f248df92adc514ea46d3526987c5928ca8fd60d72e8308e1072835fc",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation",
        "test-time-rl"
      ]
    },
    {
      "arxiv_id": "2610.00317",
      "published": "2026-09-29T02:55:12Z",
      "updated": "2026-09-29T02:55:12Z",
      "revision": 1,
      "metadata_sha256": "47e837de7a1dece7754d202a5eae37140cdb3fe3ce0023b965ddd33570c54a9d",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd"
      ]
    },
    {
      "arxiv_id": "2609.36484",
      "published": "2026-09-29T01:44:39Z",
      "updated": "2026-10-14T09:17:52Z",
      "revision": 2,
      "metadata_sha256": "3bc897905d90239eb464c17279ea13be88708cee9f7fe231ff569c3c38e94bfa",
      "repository_status": "implemented",
      "matched_queries": [
        "llm-rl",
        "on-policy-distillation",
        "opd-abbreviation",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.00309",
      "published": "2026-09-28T19:52:42Z",
      "updated": "2026-09-28T19:52:42Z",
      "revision": 1,
      "metadata_sha256": "f9d69a23df53783d22221b3db16f122c51cccba6961cbf49a3ca040c2fc075ac",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation"
      ]
    },
    {
      "arxiv_id": "2609.35445",
      "published": "2026-09-28T15:41:54Z",
      "updated": "2026-10-14T14:15:55Z",
      "revision": 4,
      "metadata_sha256": "8c4300f55fc4925ea40c3223eb26d4983ad1998e07b070091735facf2dc75a46",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.35338",
      "published": "2026-09-28T14:58:12Z",
      "updated": "2026-10-14T14:15:37Z",
      "revision": 2,
      "metadata_sha256": "dd07f36c8d0bfb663cfc76af9074af37fcc272a023dee4e5ae61c0242cf6db42",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.34474",
      "published": "2026-09-28T07:28:12Z",
      "updated": "2026-10-14T08:25:41Z",
      "revision": 2,
      "metadata_sha256": "d157a299c290e4bd26c332df190bb2192ca2f40cc828058331dd427820c45116",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.14001",
      "published": "2026-09-27T08:48:42Z",
      "updated": "2026-09-27T08:48:42Z",
      "revision": 1,
      "metadata_sha256": "55e794f1414688f8b800865fe9c619879aaaf499b529437b16f4820636d785c4",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2609.33291",
      "published": "2026-09-27T06:53:01Z",
      "updated": "2026-10-13T23:43:02Z",
      "revision": 2,
      "metadata_sha256": "2ad6b8d07719f4c71d63845f8b610ad915dccfb743361eabd1a67ca3fe634f14",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.14000",
      "published": "2026-09-27T05:25:37Z",
      "updated": "2026-09-27T05:25:37Z",
      "revision": 1,
      "metadata_sha256": "196138722cffd867f7cf6b3d77fbcdaaec808a21b7ab8fbddad1cd5003df5b0b",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13998",
      "published": "2026-09-27T03:53:05Z",
      "updated": "2026-09-27T03:53:05Z",
      "revision": 1,
      "metadata_sha256": "6b8e188dd0060442bd7c8df33e3bda69a5860f884589fc85016157d6a732ecdd",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.13995",
      "published": "2026-09-26T23:07:02Z",
      "updated": "2026-09-26T23:07:02Z",
      "revision": 1,
      "metadata_sha256": "5e6487372c502af6bca81ef58afc6de6cf5d84a48f42cee2e3680ff082deb9fa",
      "repository_status": "new",
      "matched_queries": [
        "llm-rl",
        "post-training",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.06892",
      "published": "2026-09-26T15:24:29Z",
      "updated": "2026-09-26T15:24:29Z",
      "revision": 1,
      "metadata_sha256": "5150d0e02656ec84f0d1bf8d7e0c1ec56c91ceebd7b80664122584b643a3a2b3",
      "repository_status": "reviewed",
      "matched_queries": [
        "preference-optimization",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.13989",
      "published": "2026-09-26T14:42:02Z",
      "updated": "2026-09-26T14:42:02Z",
      "revision": 1,
      "metadata_sha256": "1394ac4c2099275704912d0b3a5081cf5dde5dc434e099613625f29df094c81e",
      "repository_status": "new",
      "matched_queries": [
        "policy-llm-abbreviation",
        "preference-optimization"
      ]
    },
    {
      "arxiv_id": "2609.32429",
      "published": "2026-09-26T10:05:10Z",
      "updated": "2026-10-14T06:56:11Z",
      "revision": 2,
      "metadata_sha256": "519022d0d03d9b2a5a9b505048802b7aa3d8931587a5f58bff700d949a5becbb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.32384",
      "published": "2026-09-26T08:58:48Z",
      "updated": "2026-10-14T10:02:53Z",
      "revision": 2,
      "metadata_sha256": "24a9eaed05c5b61fe24e9cae07cf8244c83f57aef90dfcf305e19fa46962df33",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.32363",
      "published": "2026-09-26T08:41:10Z",
      "updated": "2026-10-14T10:03:45Z",
      "revision": 2,
      "metadata_sha256": "a02119d8b88657ae8ae98756a7582b455477f4c424b3865fe48905b641f59fff",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.10552",
      "published": "2026-09-25T20:48:04Z",
      "updated": "2026-09-25T20:48:04Z",
      "revision": 1,
      "metadata_sha256": "f3f00fce24e9954d1c21e3e029f7c094e0e6219cd868d3d41c38dc9fda406703",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2609.30819",
      "published": "2026-09-25T04:56:18Z",
      "updated": "2026-10-14T03:40:35Z",
      "revision": 2,
      "metadata_sha256": "de22e92696a7693c0a36c001776f40dc7967553cfce39a4ba92a83866c229f5e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.08819",
      "published": "2026-09-24T17:18:48Z",
      "updated": "2026-09-24T17:18:48Z",
      "revision": 1,
      "metadata_sha256": "285cbe5bad72aa257265c8accc8a56473d74c771278df24a9b3ee2fa8261e511",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00256",
      "published": "2026-09-24T03:29:27Z",
      "updated": "2026-09-24T03:29:27Z",
      "revision": 1,
      "metadata_sha256": "2dffeccb08d196e6738d27ddbed3abf490ed8bc6eab6d2e04f386651f1e21832",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2609.28399",
      "published": "2026-09-23T17:04:30Z",
      "updated": "2026-10-14T16:08:41Z",
      "revision": 2,
      "metadata_sha256": "1f2322ffc608871da34b17cca9f34fe820c66e22c7087925733f3412262d079c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.28248",
      "published": "2026-09-23T15:09:09Z",
      "updated": "2026-10-14T11:00:42Z",
      "revision": 2,
      "metadata_sha256": "c820cab8abe134e7a6006738475d1b3559890ffa95658b11d768ef426a1139dd",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.27043",
      "published": "2026-09-22T20:38:54Z",
      "updated": "2026-10-13T22:50:27Z",
      "revision": 2,
      "metadata_sha256": "0f457bddb66b132e895d61337de251225d7fc277c03fa29162cf101883de3192",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.00202",
      "published": "2026-09-20T11:31:26Z",
      "updated": "2026-09-20T11:31:26Z",
      "revision": 1,
      "metadata_sha256": "eeac2d9d67b68fd8223d7a7a9d0ab8f0e088bbcd1cbdc40123d939ac2499e917",
      "repository_status": "new",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00197",
      "published": "2026-09-18T20:14:09Z",
      "updated": "2026-09-18T20:14:09Z",
      "revision": 1,
      "metadata_sha256": "cb35dcf6b93f3d7fbebef5739ea5debd26cc05f1151a18d35403b974ca4ba6e1",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2609.18381",
      "published": "2026-09-16T09:36:15Z",
      "updated": "2026-10-13T21:08:56Z",
      "revision": 2,
      "metadata_sha256": "4260a856c2ded8896277353f53ee8beee08bd351d46e8cdc408c5ed9031db6b9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.13050",
      "published": "2026-09-11T16:45:36Z",
      "updated": "2026-10-14T10:47:25Z",
      "revision": 2,
      "metadata_sha256": "8a4b85ac060bf731e963e0c556e6d26b1d0cdbbcfce24f673d85c5d62256f73c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.11326",
      "published": "2026-09-10T09:56:17Z",
      "updated": "2026-09-28T15:29:30Z",
      "revision": 3,
      "metadata_sha256": "cef90d4cc56fbcde9c6199d52b4f2bb2f5868cbce263160a1cc0d89dfad1515b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.10886",
      "published": "2026-09-09T22:45:18Z",
      "updated": "2026-10-14T03:51:27Z",
      "revision": 2,
      "metadata_sha256": "4d79be49454838ddc66cff59416ad0912a4ad905cd2cd1f5b8a23295971f1a56",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.06874",
      "published": "2026-09-09T05:14:20Z",
      "updated": "2026-09-09T05:14:20Z",
      "revision": 1,
      "metadata_sha256": "52fe55a372c021842e6f3f2db04c8ad8e5003ed94c1878cef01a24fdf3aa40f9",
      "repository_status": "reviewed",
      "matched_queries": [
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2610.00096",
      "published": "2026-09-08T14:49:27Z",
      "updated": "2026-09-08T14:49:27Z",
      "revision": 1,
      "metadata_sha256": "9018761ad8e1610f7aee1cc0462b4538d8f613a28de34e5456accaf2ae3eadb4",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2609.08594",
      "published": "2026-09-08T11:30:32Z",
      "updated": "2026-10-14T06:54:42Z",
      "revision": 3,
      "metadata_sha256": "f96364f860087369b39b6e21b120ad503825dc996978d6a7ebc73ed3d587f3eb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.06154",
      "published": "2026-09-05T15:55:22Z",
      "updated": "2026-10-14T05:32:58Z",
      "revision": 2,
      "metadata_sha256": "4e8f648a0ac4d60aff413636064b2c79b221370a07d1557c9a08ac1f8313526d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.04861",
      "published": "2026-09-04T08:21:34Z",
      "updated": "2026-10-14T02:35:33Z",
      "revision": 2,
      "metadata_sha256": "f5a8ae2ef7a7ef17a3596051f9dac6f2e24d8ac3c15051ff311c3ac4fef13058",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.00047",
      "published": "2026-09-03T11:06:07Z",
      "updated": "2026-09-03T11:06:07Z",
      "revision": 1,
      "metadata_sha256": "700384263681732de165e3d4d7c4002bf61aa94e3596896982f5a04d7341b7c8",
      "repository_status": "reviewed",
      "matched_queries": [
        "process-reward",
        "reward-model"
      ]
    },
    {
      "arxiv_id": "2610.00035",
      "published": "2026-09-02T17:30:18Z",
      "updated": "2026-09-02T17:30:18Z",
      "revision": 1,
      "metadata_sha256": "d20e3fb1a075b65982cc2ac78bde9b29205a15fea86efdc95820ee1f8c92bd49",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl"
      ]
    },
    {
      "arxiv_id": "2609.01449",
      "published": "2026-09-01T15:55:01Z",
      "updated": "2026-10-14T13:47:19Z",
      "revision": 2,
      "metadata_sha256": "d455863ddabb5d3afe2869dc9583652b1f5d19b0e8bec62c6e1309ad3a45c091",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.27296",
      "published": "2026-08-27T16:01:11Z",
      "updated": "2026-10-13T21:11:02Z",
      "revision": 3,
      "metadata_sha256": "1ee1af925a01a54e0edefe41018c4d898ad88cc1644af326728027fc51ac0dde",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2609.29584",
      "published": "2026-08-27T11:47:59Z",
      "updated": "2026-10-14T13:34:11Z",
      "revision": 2,
      "metadata_sha256": "d4383cf89872efee3025f21ad068a6ded9062507202d00168b47fd68299e2a50",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.24065",
      "published": "2026-08-25T04:53:19Z",
      "updated": "2026-10-14T07:30:45Z",
      "revision": 2,
      "metadata_sha256": "475eb03514610131b79f65db1dcce3423864d42fc127e572066c205088cd0f1e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.24049",
      "published": "2026-08-25T04:18:08Z",
      "updated": "2026-10-14T12:40:23Z",
      "revision": 2,
      "metadata_sha256": "c17574d415034fad17c91ec29c07bd53d691dd7639eb0d115665494963439f97",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.12027",
      "published": "2026-08-12T13:07:19Z",
      "updated": "2026-10-14T14:48:23Z",
      "revision": 2,
      "metadata_sha256": "8b95b17037ca7ea5e35f01f7308aab2a1d333b9093ef49277996d932a222a0ae",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.11669",
      "published": "2026-08-12T05:29:21Z",
      "updated": "2026-10-13T19:52:28Z",
      "revision": 2,
      "metadata_sha256": "0d997f6b79c8419a8de82f01373025a1d2b66ab87f002917865d76858df101f2",
      "repository_status": "implemented",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.12474",
      "published": "2026-08-11T00:27:07Z",
      "updated": "2026-08-11T00:27:07Z",
      "revision": 1,
      "metadata_sha256": "1ba893e767ee63b3ad07c80a25856e157a580e9deab139f1953b7210f94986fa",
      "repository_status": "reviewed",
      "matched_queries": [
        "post-training"
      ]
    },
    {
      "arxiv_id": "2608.14706",
      "published": "2026-08-11T00:02:32Z",
      "updated": "2026-10-14T05:37:12Z",
      "revision": 2,
      "metadata_sha256": "3507b82e83a9b5907f4fa1ac333f1f317ac49fc73b35b6ed93c54f6fd5b34a0f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.10232",
      "published": "2026-08-10T21:10:46Z",
      "updated": "2026-10-13T20:03:30Z",
      "revision": 2,
      "metadata_sha256": "91bdb1d98baaabdd6200120c07bd7b118c82a05d88ec071332f10cbed2b17317",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.05025",
      "published": "2026-08-05T16:28:57Z",
      "updated": "2026-10-14T11:51:50Z",
      "revision": 3,
      "metadata_sha256": "1760bcb0bdbbfd76a1cc79449d6e8497065aec0e0b055a9a81102c50f742438c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.04962",
      "published": "2026-08-05T15:32:27Z",
      "updated": "2026-10-14T04:53:03Z",
      "revision": 2,
      "metadata_sha256": "0d5b10337734e4ebaedeb2e2d387923f3971428a8dbb08fb40bfa46422d36c0e",
      "repository_status": "implemented",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.16925",
      "published": "2026-08-04T21:20:44Z",
      "updated": "2026-10-14T09:40:45Z",
      "revision": 3,
      "metadata_sha256": "0e221025dca3aa4af1b7f586573cc3b5dd005f9f18d3e4bb7579c4f37fb8fcb7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2608.03172",
      "published": "2026-08-04T06:04:18Z",
      "updated": "2026-10-14T07:46:56Z",
      "revision": 5,
      "metadata_sha256": "7e9e435ac175229b5ccdd470e67fd2cf6cdcf450b0dc6a929a1efb4efe89d735",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.29606",
      "published": "2026-07-31T16:38:47Z",
      "updated": "2026-10-14T15:20:16Z",
      "revision": 3,
      "metadata_sha256": "6755026a4a845b08c6ef08830a166b74fd4f2e613ca62ad3e62f71295e75830e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.24041",
      "published": "2026-07-27T06:30:49Z",
      "updated": "2026-10-14T17:50:43Z",
      "revision": 3,
      "metadata_sha256": "b424ee4fde67dbba397299d4f852cebb73c1540e9df05599ee954d35465664cb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.22299",
      "published": "2026-07-24T13:44:36Z",
      "updated": "2026-10-13T18:04:05Z",
      "revision": 2,
      "metadata_sha256": "ebd0bbaa942e694f7031d0b8432c990487f15af95bf8d33f20ef190373544fd1",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.15482",
      "published": "2026-07-16T21:57:27Z",
      "updated": "2026-10-14T09:30:54Z",
      "revision": 2,
      "metadata_sha256": "ec6b45225523ad002a193bf14d75911d4288b68942f0a4fb0461c8737d688c9f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.13609",
      "published": "2026-07-15T08:56:57Z",
      "updated": "2026-10-14T07:00:30Z",
      "revision": 2,
      "metadata_sha256": "5a56b0ad8f67443587454221dbce3d995719246f236bd5e85bc3e3e66a3a5816",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.13319",
      "published": "2026-07-14T22:59:40Z",
      "updated": "2026-10-14T06:06:18Z",
      "revision": 3,
      "metadata_sha256": "833700475ba75498b9f4003383201d20acacfd45df99f39da86bfc4eaf8e709f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.12645",
      "published": "2026-07-14T11:23:51Z",
      "updated": "2026-10-14T03:57:37Z",
      "revision": 2,
      "metadata_sha256": "eeb426bf6c6a205d50b82e330c32bbe9462c68ee3bb6ba50ff00a6a6a62d9c1f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.10669",
      "published": "2026-07-12T09:27:57Z",
      "updated": "2026-10-14T06:17:33Z",
      "revision": 3,
      "metadata_sha256": "ea668a9d52bc438fc0979c7b848841f0de8cb62a240fe7b0a24fd7f87b51736a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.10203",
      "published": "2026-07-11T08:27:33Z",
      "updated": "2026-10-14T02:15:14Z",
      "revision": 4,
      "metadata_sha256": "f798490727f410dbfb4a58a6625ef4a49db825ec42edc139c6a853c630ee7327",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.09015",
      "published": "2026-07-10T00:42:10Z",
      "updated": "2026-10-13T20:50:09Z",
      "revision": 2,
      "metadata_sha256": "059f17b9b0e955183edda9fba72e5dd017e3f5de0ef5ca1d4a1fa901040078c5",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.08234",
      "published": "2026-07-09T08:29:38Z",
      "updated": "2026-10-13T19:58:25Z",
      "revision": 2,
      "metadata_sha256": "66984f3c37e42e89b4c2cc09d5737d94c51777f6fc24f4b87db5848e77920438",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.08093",
      "published": "2026-07-09T04:03:26Z",
      "updated": "2026-10-14T02:19:46Z",
      "revision": 2,
      "metadata_sha256": "f9fa7bd657bb550c1006b844bce997c9164a543ec2e730277035cef8e216064b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2610.06861",
      "published": "2026-07-08T14:38:06Z",
      "updated": "2026-07-08T14:38:06Z",
      "revision": 1,
      "metadata_sha256": "d44f859f7975e760c7676d489f531c8980bb641fdad4b4becf444989875dd4e4",
      "repository_status": "reviewed",
      "matched_queries": [
        "llm-rl",
        "policy-llm-abbreviation",
        "reward-model",
        "rlvr-abbreviation"
      ]
    },
    {
      "arxiv_id": "2607.05381",
      "published": "2026-07-06T17:56:11Z",
      "updated": "2026-10-14T17:57:33Z",
      "revision": 2,
      "metadata_sha256": "77fe2bf3b2c0a4b7d89be3ea24cfc661fcc6a661a443216566e43766483254f9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.05175",
      "published": "2026-07-06T14:57:26Z",
      "updated": "2026-10-14T03:01:50Z",
      "revision": 2,
      "metadata_sha256": "8783d4c0822a032b2a8709c6c080276946552b11ea00e899e0b4a38c6bafbf41",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2607.02417",
      "published": "2026-07-02T16:48:43Z",
      "updated": "2026-10-13T22:58:41Z",
      "revision": 2,
      "metadata_sha256": "67c26dc0b4745d38b533203df775b7788c163a3d04747045cab27e83506af4af",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.29403",
      "published": "2026-06-28T13:50:13Z",
      "updated": "2026-10-13T18:02:06Z",
      "revision": 3,
      "metadata_sha256": "32bb37667c3a161336ed8c57a3da762c46e0992c7073be425ee71a06a629d33d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.29240",
      "published": "2026-06-28T07:11:05Z",
      "updated": "2026-10-14T05:34:14Z",
      "revision": 3,
      "metadata_sha256": "818f8dbcc121b3b3682d68a518fa60babe484b0bb86000349b182fd607770817",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.26277",
      "published": "2026-06-24T18:18:56Z",
      "updated": "2026-10-14T17:04:12Z",
      "revision": 3,
      "metadata_sha256": "cf8637323289aa520ac022bcf6c17c05f10b376e6dc40cab218a8a5b1305b7a0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.24967",
      "published": "2026-06-23T10:07:34Z",
      "updated": "2026-10-13T21:47:42Z",
      "revision": 3,
      "metadata_sha256": "4755979368fdc38380651bc21eaec9b50a384810703bb7a7635534c14d75fadf",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.22278",
      "published": "2026-06-21T00:11:46Z",
      "updated": "2026-10-14T16:28:57Z",
      "revision": 2,
      "metadata_sha256": "ea4d7c15d33ad2d993ec419b1f660e570b11abab62e89dfb425b492fa51fdbd8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.21139",
      "published": "2026-06-19T06:24:05Z",
      "updated": "2026-10-14T12:18:57Z",
      "revision": 2,
      "metadata_sha256": "c26c03623ab9b7f8be7d3c4475a806af1c53b86f032805e0ed9e976c2eb82599",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.17029",
      "published": "2026-06-15T17:52:27Z",
      "updated": "2026-10-14T09:24:07Z",
      "revision": 2,
      "metadata_sha256": "c222818c5885036b1c150976d1348752bea43f58caed784cacb6bd09a8d20e9a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.16710",
      "published": "2026-06-15T13:40:01Z",
      "updated": "2026-10-14T09:21:50Z",
      "revision": 2,
      "metadata_sha256": "4c1aea1012b89018637ede058600ca657d95c99bc79e49e198b0f2af60ba81f0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.16285",
      "published": "2026-06-15T06:49:18Z",
      "updated": "2026-10-14T01:37:07Z",
      "revision": 3,
      "metadata_sha256": "3bec64233ae4859a9a6634d352a75d2909da193dcbace36d280f918a1eef3802",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.15251",
      "published": "2026-06-13T11:15:04Z",
      "updated": "2026-10-14T15:04:59Z",
      "revision": 2,
      "metadata_sha256": "18afaed2de8fdbb1b4602d9f5f34aa6ef099177a471bd3cb4b6141e3d4d6f521",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.13349",
      "published": "2026-06-11T13:38:23Z",
      "updated": "2026-10-14T13:33:49Z",
      "revision": 2,
      "metadata_sha256": "bc4ad245469c71cbd0d02c45bd2fab72d0e2bfa4269b1f358be37010a653bed6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.11350",
      "published": "2026-06-09T18:26:24Z",
      "updated": "2026-10-14T00:58:36Z",
      "revision": 2,
      "metadata_sha256": "26df70e7f810c677aa7463bd0bb32921307ea39372d89cb60ea3687bbd2635e2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.09653",
      "published": "2026-06-08T15:42:39Z",
      "updated": "2026-10-14T10:25:47Z",
      "revision": 2,
      "metadata_sha256": "44c6f54022fff97f8047146a72a134681523c02c2a81babf8adc4200bfa2cbb6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.09138",
      "published": "2026-06-08T07:35:18Z",
      "updated": "2026-10-14T02:20:50Z",
      "revision": 2,
      "metadata_sha256": "5ab195ea77c74380dac7e5330d6ac9f9669bab764776649f40b53e7cb479b9ec",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.08682",
      "published": "2026-06-07T15:34:59Z",
      "updated": "2026-10-14T13:34:57Z",
      "revision": 2,
      "metadata_sha256": "419f927bb01bc397a1bd76267df702f2e7bae4a1db5981477ca339882dfb119d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.07036",
      "published": "2026-06-05T08:26:44Z",
      "updated": "2026-10-14T05:30:57Z",
      "revision": 3,
      "metadata_sha256": "d65310dea6f3434bebf8e0c0c0324e55a01bc3cef5db1a5353a3dd03cddc184f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.07690",
      "published": "2026-06-05T06:31:43Z",
      "updated": "2026-10-13T19:14:39Z",
      "revision": 2,
      "metadata_sha256": "231941712f4f5f5d0017fe637336124f2c146cbfa55f93b9492d31a83d21fda6",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.06788",
      "published": "2026-06-05T00:14:44Z",
      "updated": "2026-10-14T13:55:08Z",
      "revision": 2,
      "metadata_sha256": "cb3d3375e5736e4b3047f0afa6c876358ffb1b608d7f42cc6d5ab1e1f33e9096",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.06177",
      "published": "2026-06-04T13:52:21Z",
      "updated": "2026-10-14T16:56:04Z",
      "revision": 2,
      "metadata_sha256": "c6257742f7dd615608307b1702f3be41c13c6a30fc54e798da3ceba14dfa08bf",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.02994",
      "published": "2026-06-02T01:11:15Z",
      "updated": "2026-10-14T02:22:53Z",
      "revision": 2,
      "metadata_sha256": "e08abbe0f489d00c2898476e2b8028c913a97bf40834d40c1e7c6fcdd152f59e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2606.00981",
      "published": "2026-05-31T03:28:42Z",
      "updated": "2026-10-14T07:03:15Z",
      "revision": 2,
      "metadata_sha256": "99043ac3bf4abf01d43114af6e4c425d74edec98b75687798cf530556d0b3296",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.31163",
      "published": "2026-05-29T11:13:00Z",
      "updated": "2026-10-14T01:01:27Z",
      "revision": 5,
      "metadata_sha256": "ee27df1bbfc69059521e230811f54186098e9f91e1e47a14a02dfed4db0bbc35",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.31111",
      "published": "2026-05-29T10:23:48Z",
      "updated": "2026-10-08T19:10:10Z",
      "revision": 3,
      "metadata_sha256": "ea9bbade516de9ca943934b1b849637b8a735c31b6218b0bd3b2c7d6e6090d6e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.29054",
      "published": "2026-05-27T19:57:15Z",
      "updated": "2026-10-14T01:20:45Z",
      "revision": 3,
      "metadata_sha256": "a5d23379fc8a402a4fe52c27328afc784e332c7886499dacf8fe7d572344066d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.28165",
      "published": "2026-05-27T08:47:50Z",
      "updated": "2026-10-14T09:14:04Z",
      "revision": 2,
      "metadata_sha256": "e96cc8d570620846f99280b6e1af286a7bbf31d738baec06d0320e255e1a9772",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.28093",
      "published": "2026-05-27T07:51:46Z",
      "updated": "2026-10-14T16:22:16Z",
      "revision": 3,
      "metadata_sha256": "68982847345bcba17da2e6a6beb36bd4e1853f6b8450437d8c58ae13980d02e2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.23258",
      "published": "2026-05-22T06:00:15Z",
      "updated": "2026-10-13T19:50:35Z",
      "revision": 2,
      "metadata_sha256": "f181673d97b42a1fe15325100772346a52036497574eeb53e922d5b24132d16e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.20364",
      "published": "2026-05-19T18:16:58Z",
      "updated": "2026-10-14T11:05:55Z",
      "revision": 2,
      "metadata_sha256": "5267c8f99b8bcfe636d15034760ecf6243c7a9cf3c5f908b91b9d0a55d71a2fc",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.19660",
      "published": "2026-05-19T10:53:03Z",
      "updated": "2026-10-14T05:26:57Z",
      "revision": 3,
      "metadata_sha256": "eb961abe5e7c117d13234fd022b96d9736ea81eabb8cb6e2e21decd9c47def52",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.19330",
      "published": "2026-05-19T04:07:41Z",
      "updated": "2026-10-14T17:35:11Z",
      "revision": 2,
      "metadata_sha256": "9b1e4e259e2865d7db3b69646d5fcf0a06a398ec57a7ccc29c40222b0f3e2e7d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.19324",
      "published": "2026-05-19T04:03:01Z",
      "updated": "2026-10-14T17:34:35Z",
      "revision": 2,
      "metadata_sha256": "9ed44c62987cce18c50ca02aa0cfd99edc03082443ad1e384071c5b56c6b4e4a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.19156",
      "published": "2026-05-18T22:20:33Z",
      "updated": "2026-10-13T18:20:13Z",
      "revision": 2,
      "metadata_sha256": "c07a2fd3537871dae571ad4d21b1728f3585df55953b8461569174d22dcd8aad",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.18106",
      "published": "2026-05-18T09:17:26Z",
      "updated": "2026-10-14T03:08:02Z",
      "revision": 5,
      "metadata_sha256": "30b446d5af4c6e44d41a096bfec9caa594bf93f94468664eb6675c6da0cc4f19",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.15959",
      "published": "2026-05-15T13:54:03Z",
      "updated": "2026-10-13T23:38:36Z",
      "revision": 2,
      "metadata_sha256": "44c3386d12b90062ab2ded9e7852fe2e26ecc89618491ef305d22ecd0f5cd280",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.15470",
      "published": "2026-05-14T23:17:21Z",
      "updated": "2026-10-14T11:32:13Z",
      "revision": 3,
      "metadata_sha256": "beb19031d0e965a17e087c086bc0869586a3f29542b2ccc7379ef7e62dcf6a3e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.22845",
      "published": "2026-05-14T17:12:44Z",
      "updated": "2026-10-13T23:27:46Z",
      "revision": 3,
      "metadata_sha256": "4e6df09b31725a70845c970b6d28a6cb1136dc280d885bc8f95d8755dbded03f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.15250",
      "published": "2026-05-14T15:50:01Z",
      "updated": "2026-10-14T11:15:57Z",
      "revision": 4,
      "metadata_sha256": "094bbe336cd4f4a931949574e841f8fdb1a06900d13e40cc6f0ebbea5ee1b8bd",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.12484",
      "published": "2026-05-12T17:58:20Z",
      "updated": "2026-10-14T09:07:21Z",
      "revision": 3,
      "metadata_sha256": "7d3733ad87087c77aaa13702293868b8b8e54d705005750d6caf48c178fadba3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.12461",
      "published": "2026-05-12T17:48:09Z",
      "updated": "2026-10-14T09:23:20Z",
      "revision": 2,
      "metadata_sha256": "0541e2ac834d07de6b9affee66a549fb3342a538dcda3b38ba18be12e986859d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.12000",
      "published": "2026-05-12T11:49:08Z",
      "updated": "2026-10-14T10:51:06Z",
      "revision": 3,
      "metadata_sha256": "49d0b74675cde10c53c75c5da61ea0b4f377c2911f8f49e291131129878c60f1",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.10659",
      "published": "2026-05-11T14:41:11Z",
      "updated": "2026-10-13T20:12:03Z",
      "revision": 3,
      "metadata_sha256": "735c4d745357794939123f7cb5ea95492d2d354dc4b246d248ede3f86d92fe36",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.09742",
      "published": "2026-05-10T20:34:06Z",
      "updated": "2026-10-14T12:16:33Z",
      "revision": 3,
      "metadata_sha256": "2b75b0cc94f6ad81511f9d253eb1ff9c3fa93fe664eafb65681b1317ad981432",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.09424",
      "published": "2026-05-10T08:52:28Z",
      "updated": "2026-10-14T13:51:21Z",
      "revision": 2,
      "metadata_sha256": "b8d07a046a42f5bd43a878bbea6006163a62bb67f06d993dc3968bfedb5dced2",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.08733",
      "published": "2026-05-09T06:36:32Z",
      "updated": "2026-10-14T09:59:19Z",
      "revision": 2,
      "metadata_sha256": "75a0c70c166c93a0f25ecffa5ed536156e66ff5836c6676c4577f9682661eae0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.10980",
      "published": "2026-05-09T03:26:23Z",
      "updated": "2026-10-14T11:15:08Z",
      "revision": 2,
      "metadata_sha256": "40aa9e125747d16e12603434e985d0a344888c5e71257a3ea663b345152ec975",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.07191",
      "published": "2026-05-08T03:39:38Z",
      "updated": "2026-10-14T13:35:30Z",
      "revision": 2,
      "metadata_sha256": "4c670fffb1bdb20a52e1a535fc5a89031a99d05e51f32d0c1fb6860731803cbf",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.07057",
      "published": "2026-05-08T00:12:03Z",
      "updated": "2026-10-14T17:48:13Z",
      "revision": 2,
      "metadata_sha256": "3ace1767218f622e92081fbb0a6c07bb5c6b22375fb914fe5f3eeca65946a983",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2605.06727",
      "published": "2026-05-07T11:26:09Z",
      "updated": "2026-10-14T15:02:17Z",
      "revision": 2,
      "metadata_sha256": "afb4d9fde1e980c639c9cc929fd2afd0f7c2d3efe66bcfdf08aa942dc0fcdeae",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.26370",
      "published": "2026-04-29T07:30:33Z",
      "updated": "2026-10-14T14:28:53Z",
      "revision": 2,
      "metadata_sha256": "373c63e32633a7350ffb3c50ef7b679f0d7b854f49b3de86fdf4efebdf2e6399",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.25572",
      "published": "2026-04-28T12:41:20Z",
      "updated": "2026-10-14T14:10:18Z",
      "revision": 2,
      "metadata_sha256": "a1d26deb0d234ce580b2017a54edfddae4a321ab3670f962d594a2d43f052adb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.23069",
      "published": "2026-04-24T23:39:49Z",
      "updated": "2026-10-14T04:04:03Z",
      "revision": 2,
      "metadata_sha256": "a107c92cde4459d92337df2a1b56523e5672d16e66b698a21117f830fef96468",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.21334",
      "published": "2026-04-23T06:45:36Z",
      "updated": "2026-10-14T09:00:41Z",
      "revision": 3,
      "metadata_sha256": "3964fcfd3062b8bfdd3604828f2dc841277e7e8e9fa9a3abc15561175900c0de",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.18508",
      "published": "2026-04-20T17:00:17Z",
      "updated": "2026-10-13T20:40:04Z",
      "revision": 2,
      "metadata_sha256": "7d69b3858ab59c15146e4a740cc3e6a244623f23836e29305800c80b71f72b30",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.18360",
      "published": "2026-04-20T14:50:33Z",
      "updated": "2026-10-14T06:38:52Z",
      "revision": 4,
      "metadata_sha256": "dc5b6c1f16116094e5066dc98cc319208484e11596300d469e10beb7c2d7102d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.17998",
      "published": "2026-04-20T09:24:28Z",
      "updated": "2026-10-14T13:48:21Z",
      "revision": 2,
      "metadata_sha256": "36165a5db052577f49dbc1abe1d1aeaf37cdccaf112b2792564c60ae17c17123",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.17886",
      "published": "2026-04-20T06:57:50Z",
      "updated": "2026-10-14T13:27:25Z",
      "revision": 3,
      "metadata_sha256": "05cbe9c89b23377bd7fdad3790022377e6cc54ca811c23f596d1fc34fc591d68",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.17883",
      "published": "2026-04-20T06:53:32Z",
      "updated": "2026-10-13T18:49:02Z",
      "revision": 2,
      "metadata_sha256": "f0fc91c2adfa18d8554e7f25d583a56da46df6cfa657522dbfba6ae84f7710bd",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.13993",
      "published": "2026-04-15T15:36:26Z",
      "updated": "2026-10-14T15:56:56Z",
      "revision": 2,
      "metadata_sha256": "d996de9ce6f7a86d8e72b60f7e934316140ba42f9222ce22ec883dbac19e1ee3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.12128",
      "published": "2026-04-13T23:23:02Z",
      "updated": "2026-10-14T01:32:05Z",
      "revision": 2,
      "metadata_sha256": "2c39d03c9f0f25b38e07ec6087c0f09143dce05bbda2fd7a147a815e86728767",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.08905",
      "published": "2026-04-10T03:13:19Z",
      "updated": "2026-10-13T18:57:50Z",
      "revision": 2,
      "metadata_sha256": "ec233b434ad195177e29695fea9d2d361259a3814cfe387c1b9f6d8e17caac3e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.03925",
      "published": "2026-04-05T01:35:50Z",
      "updated": "2026-10-14T01:03:52Z",
      "revision": 2,
      "metadata_sha256": "bc4d7a55a64a5dce36e6efa9dd7a9e515e9248d70896d8420106b024b889871f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.25923",
      "published": "2026-04-01T10:29:43Z",
      "updated": "2026-10-14T06:43:26Z",
      "revision": 2,
      "metadata_sha256": "635d48e0f02e6ee06c096f5a4f69768f3eba4eb4b4694cd494ff60d5b651cb49",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2604.00073",
      "published": "2026-03-31T14:14:47Z",
      "updated": "2026-10-14T14:23:23Z",
      "revision": 4,
      "metadata_sha256": "12e59ccf1a693abe3da311383dc08376202dc405352578b0ed7800c6cb53105b",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.28916",
      "published": "2026-03-30T18:45:54Z",
      "updated": "2026-10-14T12:00:44Z",
      "revision": 3,
      "metadata_sha256": "5c8e7f37bd1f75dfd33d6b90d5b050bb050061edd7fc3023754b62dae34e9b4f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.26030",
      "published": "2026-03-27T02:59:32Z",
      "updated": "2026-10-14T09:46:27Z",
      "revision": 2,
      "metadata_sha256": "7fe7e130b8e3595faccf2a7955a2b50a7042d9ce09b5d3b709d115d1cf49b4df",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.23678",
      "published": "2026-03-24T19:33:44Z",
      "updated": "2026-10-13T21:12:12Z",
      "revision": 2,
      "metadata_sha256": "45c4f610652a120b555ceacdae2e5776a9abacf4791ad257af1eb10755e61202",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.23305",
      "published": "2026-03-24T15:11:04Z",
      "updated": "2026-10-14T16:49:56Z",
      "revision": 2,
      "metadata_sha256": "52674a36c0df7575b6d439081cbf05f7a2f7901a552967e1916087c47ccb8aa4",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.19714",
      "published": "2026-03-20T07:35:38Z",
      "updated": "2026-10-14T06:34:29Z",
      "revision": 2,
      "metadata_sha256": "cadef7453f6db1023cf84086beaf952f4c5428a1b504ec7710dbe7252ac11883",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.18965",
      "published": "2026-03-19T14:30:08Z",
      "updated": "2026-10-13T18:32:32Z",
      "revision": 2,
      "metadata_sha256": "aaa2ff5d3d6771abd3e181197709d42ecbcac2746cc9c36192556dcc57094d22",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.16557",
      "published": "2026-03-17T14:19:05Z",
      "updated": "2026-10-14T04:23:03Z",
      "revision": 2,
      "metadata_sha256": "870e173b4ccddb57a941c289fbea2a1f85ba652f573ca8c9219844cadeb7a3f9",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.13535",
      "published": "2026-03-13T19:16:17Z",
      "updated": "2026-09-30T13:48:45Z",
      "revision": 5,
      "metadata_sha256": "6b6a9600fd63e9950ed17cc2d340b129f8f6d4826ca63906d6f119819c58a7e7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.09200",
      "published": "2026-03-10T05:18:48Z",
      "updated": "2026-10-14T03:22:44Z",
      "revision": 2,
      "metadata_sha256": "70511d9f178fcdf525ff77234500e759c4fdc44a1cc1678503cb9858fcd2a812",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.06977",
      "published": "2026-03-07T01:35:52Z",
      "updated": "2026-10-13T18:05:59Z",
      "revision": 3,
      "metadata_sha256": "3a7ce76b6430c3f6dd10264e0af7b8f0cfada306390f80e4bf317252c9d1aa15",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.04949",
      "published": "2026-03-05T08:43:06Z",
      "updated": "2026-10-14T10:16:21Z",
      "revision": 4,
      "metadata_sha256": "95f3e1a61f82de8f32b4c3e567244198b8f39f508a4e234fefd4988ff7db571a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.01502",
      "published": "2026-03-02T06:21:43Z",
      "updated": "2026-10-14T11:24:09Z",
      "revision": 2,
      "metadata_sha256": "b9de9956628aa3e60e331047fccfe8c64e6142ba275dac43f21e8c2bb80faf27",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.00720",
      "published": "2026-02-28T15:58:28Z",
      "updated": "2026-10-13T23:15:42Z",
      "revision": 2,
      "metadata_sha256": "897595ffa1558b01456b41eac21a4fa1470508b55e42759fb13ae09d37aac94a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.00578",
      "published": "2026-02-28T09:57:52Z",
      "updated": "2026-10-14T05:17:40Z",
      "revision": 2,
      "metadata_sha256": "684393ea1987fb03f49282af671a8ab2063857403e61d7c28178b898307ab0a7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2603.00191",
      "published": "2026-02-27T02:31:00Z",
      "updated": "2026-10-14T08:43:34Z",
      "revision": 5,
      "metadata_sha256": "6edc550f889957247f2b4e427a69bef1936322fbe919bf3c2a22f19d2efccef3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.12881",
      "published": "2026-02-13T12:31:30Z",
      "updated": "2026-10-14T12:21:33Z",
      "revision": 2,
      "metadata_sha256": "5ed186a7221445b567e8287ad4957bdc1379fe10aa2cf9e137e9774af40092b3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.11965",
      "published": "2026-02-12T14:00:44Z",
      "updated": "2026-10-14T07:02:41Z",
      "revision": 2,
      "metadata_sha256": "50c7eb0a0fcc1f5c278124dd007b4dbdeaac56d66e35597bf287b4cb314e2e7f",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.10326",
      "published": "2026-02-10T22:03:13Z",
      "updated": "2026-10-14T01:30:26Z",
      "revision": 3,
      "metadata_sha256": "b642f0bf8c8e2af81f487b54b2ed45dc7f28275d4b15517350478022b4bf30e5",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.09009",
      "published": "2026-02-09T18:54:18Z",
      "updated": "2026-10-13T21:55:31Z",
      "revision": 4,
      "metadata_sha256": "30a5f695e50f0c4cd519c3c3d2aa94e0703847e3be9112092b3ab6faf79db8ba",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.08519",
      "published": "2026-02-09T11:07:24Z",
      "updated": "2026-10-14T13:44:07Z",
      "revision": 2,
      "metadata_sha256": "af806979290b3d160a83882ff89c05c4033779a726605d948ec1014db00c5b1d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.08318",
      "published": "2026-02-09T06:48:45Z",
      "updated": "2026-10-14T03:01:43Z",
      "revision": 3,
      "metadata_sha256": "a058bf9ca28b757b0755a7e7f0605ad971117ad9e49ca2701517a8bd86be6e66",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.08302",
      "published": "2026-02-09T06:16:43Z",
      "updated": "2026-10-14T05:57:15Z",
      "revision": 3,
      "metadata_sha256": "be227de37dfe4df42e87d1b9dc48aa14897471446ac913bccf62081a662f8ed1",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.07599",
      "published": "2026-02-07T16:01:10Z",
      "updated": "2026-10-14T11:51:03Z",
      "revision": 2,
      "metadata_sha256": "c6adc506f11ff019c060bc0bf2b33ad8caf8526b4e34c2b57e2dabd7f720220c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.07549",
      "published": "2026-02-07T13:50:38Z",
      "updated": "2026-10-13T22:09:53Z",
      "revision": 3,
      "metadata_sha256": "e243dbab2d422b1864839b4d6540ff0d9ca5d90ea5bf3baff85fdaf7132b6a15",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.02326",
      "published": "2026-02-02T16:52:09Z",
      "updated": "2026-10-14T15:10:55Z",
      "revision": 3,
      "metadata_sha256": "8da6dc6416215174fc53309a977c04c4aeb7050f82bc3d8004640a0f39ec78ab",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2602.00717",
      "published": "2026-01-31T13:20:18Z",
      "updated": "2026-10-14T17:17:43Z",
      "revision": 2,
      "metadata_sha256": "77ede7f66802ee382889e5ee25f87bc7188053a53f0770515dab2cfae426d0ca",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2601.22050",
      "published": "2026-01-29T17:49:44Z",
      "updated": "2026-10-14T08:32:20Z",
      "revision": 2,
      "metadata_sha256": "d9dd2bbe4a2ac4f2edd92d4373fb42a9a817816e1706c2782ae896570a6e465a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2601.21649",
      "published": "2026-01-29T12:49:25Z",
      "updated": "2026-10-13T18:52:58Z",
      "revision": 2,
      "metadata_sha256": "a87515d27a4fb9729d67cee196d4d82473587ddabb6bb7e58a8b440c599afc00",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2601.16834",
      "published": "2026-01-23T15:35:33Z",
      "updated": "2026-10-12T22:18:42Z",
      "revision": 4,
      "metadata_sha256": "8d6aa25a6fa411975eff7b897916ebedf67a39b40ba752517eb6084c41df0925",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2601.20875",
      "published": "2026-01-19T00:22:06Z",
      "updated": "2026-10-14T12:40:38Z",
      "revision": 3,
      "metadata_sha256": "44c3cc2dd93bcb4cd8ffbcf4c7648f6c8bb220f7add61d62b6563ab6a055346c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2601.12355",
      "published": "2026-01-18T11:26:31Z",
      "updated": "2026-10-14T16:07:08Z",
      "revision": 3,
      "metadata_sha256": "96b2d82870100e68e77dc7eed03c1badb05abfd99f6d97d59954b093b5fa91e7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2601.10085",
      "published": "2026-01-15T05:21:54Z",
      "updated": "2026-10-13T20:27:41Z",
      "revision": 3,
      "metadata_sha256": "66c3e6c553d498678178e28d83b27886b1d0e8fbdd04f280d7063a1e26e93417",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2601.08689",
      "published": "2026-01-13T16:14:23Z",
      "updated": "2026-10-14T03:51:15Z",
      "revision": 3,
      "metadata_sha256": "90b12e917b93a72106df8c6a1b15510fab30b13800e13ef776f153d2b333ae19",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2601.07871",
      "published": "2026-01-10T23:30:49Z",
      "updated": "2026-10-14T14:28:24Z",
      "revision": 2,
      "metadata_sha256": "077fbc6a5e08e31d6fbb71eb3cb89cc8009d880be2a3d5cc4467db44ecd801db",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2512.22814",
      "published": "2025-12-28T07:03:20Z",
      "updated": "2026-10-14T16:10:03Z",
      "revision": 2,
      "metadata_sha256": "e2635a03314d8fab2c044518c0c230806186f8fa2467ec97e3896d2d47ddaa71",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2512.13399",
      "published": "2025-12-15T14:50:08Z",
      "updated": "2026-10-13T21:12:48Z",
      "revision": 3,
      "metadata_sha256": "bbfe3df37b8ef9f33545945e90eadb0a3ab57e1b60a0c8306b720ebd250d697e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2512.12066",
      "published": "2025-12-12T22:29:13Z",
      "updated": "2026-10-14T02:11:31Z",
      "revision": 4,
      "metadata_sha256": "f4df15d00d11b1458eda04945f6754f89d251d10395f360b46473800e83dd663",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2512.10309",
      "published": "2025-12-11T05:55:44Z",
      "updated": "2026-10-14T09:28:20Z",
      "revision": 3,
      "metadata_sha256": "fe38ea550d622a800b81a1f363e601c08ab4c2e71b14a3241b20c4f808c6df5a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2511.10831",
      "published": "2025-11-13T22:20:20Z",
      "updated": "2026-10-14T11:44:48Z",
      "revision": 3,
      "metadata_sha256": "161ed5d83d3a51684746102df172742908fc716b668d3ecd013efd3bab916b2e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2511.08860",
      "published": "2025-11-12T00:35:54Z",
      "updated": "2026-10-14T15:30:32Z",
      "revision": 3,
      "metadata_sha256": "d914b8ad07ad7bd4f1d132a318fc939ce396cff7549bb2d229f7d0225e793bd5",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2511.04473",
      "published": "2025-11-06T15:45:18Z",
      "updated": "2026-10-14T08:53:00Z",
      "revision": 4,
      "metadata_sha256": "b44c7191f8d8c73117802e3fdeb1842fd91ff4b08e4739fb949bad121abceb96",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2511.02657",
      "published": "2025-11-04T15:34:59Z",
      "updated": "2026-10-14T06:25:03Z",
      "revision": 4,
      "metadata_sha256": "c3157a6f4c046a624562721de0cfcf40a430beb3db218d5d3d18e93fc060b210",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2510.23160",
      "published": "2025-10-27T09:39:22Z",
      "updated": "2026-10-14T14:53:40Z",
      "revision": 2,
      "metadata_sha256": "80b0de3f6520cf0ec16a5c90003420c48e84b0cf182a66896ef8e340de2ebae7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2510.22833",
      "published": "2025-10-26T21:01:30Z",
      "updated": "2026-10-14T10:19:05Z",
      "revision": 3,
      "metadata_sha256": "1cc5da3f41a48b71fda6653e387674013bd1da1d96b6e155edd723f7ce4c0c8c",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2510.13928",
      "published": "2025-10-15T13:28:49Z",
      "updated": "2026-10-14T01:11:53Z",
      "revision": 3,
      "metadata_sha256": "5c7d0990b46efed4894628f0459c1b3cf0901528c570bac070699cef90d5cbcc",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2510.12306",
      "published": "2025-10-14T09:06:14Z",
      "updated": "2026-10-13T21:04:48Z",
      "revision": 4,
      "metadata_sha256": "4ae5fccd3897c3902c75712b069bde1774fdeb8d77ff37c8ca7dc33d65eecd38",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2510.08464",
      "published": "2025-10-09T17:07:30Z",
      "updated": "2026-10-14T05:23:36Z",
      "revision": 2,
      "metadata_sha256": "b88cb4b6d0648ddcf8f4aeaf5600948f14c6328ad24d55910a2ac178ca630784",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2510.07231",
      "published": "2025-10-08T17:00:49Z",
      "updated": "2026-10-14T04:49:22Z",
      "revision": 5,
      "metadata_sha256": "a3c4bcbe1d252af5f65ce640437f452759ed3b39b1f574814166bf52aea57d19",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2509.23209",
      "published": "2025-09-27T09:42:19Z",
      "updated": "2026-10-14T08:35:06Z",
      "revision": 2,
      "metadata_sha256": "a5455d8b96fbca0eda5f7aaa81e6ab4ed9703366d7c38c8db9f92a8da12f9607",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2509.21193",
      "published": "2025-09-25T14:05:55Z",
      "updated": "2026-10-14T02:24:00Z",
      "revision": 2,
      "metadata_sha256": "38b794815b940f4d1f2cf89a6544e3ef44cb2b9a87509175c873742a3f2c86a3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2509.20645",
      "published": "2025-09-25T01:02:27Z",
      "updated": "2026-10-13T18:26:56Z",
      "revision": 4,
      "metadata_sha256": "137805f63ffc7d83355728a9773bf8dd16ff24cf0329783d12fd6332825b95f8",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2508.16939",
      "published": "2025-08-23T08:16:14Z",
      "updated": "2026-10-13T19:33:10Z",
      "revision": 2,
      "metadata_sha256": "7f32735d2fc90b8e34035395e506a6b86b3333e639726f75badaae6abd54fb51",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2508.06149",
      "published": "2025-08-08T09:11:05Z",
      "updated": "2026-10-14T06:13:56Z",
      "revision": 2,
      "metadata_sha256": "cc48b6636f721a6c6cb44916e2e0efecd5d9c8304cfaa735ac1b32b9dbcea5db",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2508.03829",
      "published": "2025-08-05T18:19:00Z",
      "updated": "2026-10-13T21:51:12Z",
      "revision": 3,
      "metadata_sha256": "9928e24692566221c87972c81795b2ad248acae390569f6b5153fee038acd3df",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2507.19465",
      "published": "2025-07-25T17:50:43Z",
      "updated": "2026-10-13T23:13:52Z",
      "revision": 2,
      "metadata_sha256": "d9a07617607c219ef393c0533aa4ac0337763756460e83e82d2f5bf6df69d5c0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2507.14843",
      "published": "2025-07-20T07:04:08Z",
      "updated": "2026-10-14T06:13:12Z",
      "revision": 5,
      "metadata_sha256": "d12b072212d9352834c6ec799c3aa452c1637f19cc8d4687e1d8265b406b63de",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2507.13638",
      "published": "2025-07-18T03:53:16Z",
      "updated": "2026-10-14T12:48:42Z",
      "revision": 4,
      "metadata_sha256": "46dcc2eae782560b264f9204bd74d01a19414e1ae22bd92a3bfcf9b2e24ba228",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2507.12553",
      "published": "2025-07-16T18:04:26Z",
      "updated": "2026-10-13T21:05:35Z",
      "revision": 4,
      "metadata_sha256": "6aefa28d42d4a7931c21fadd926f442f842b1deb911ed17cfbf4b93485133905",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2506.20642",
      "published": "2025-06-25T17:37:59Z",
      "updated": "2026-10-14T02:34:19Z",
      "revision": 3,
      "metadata_sha256": "64f13ad8a87e13d32eb77533c60ebc18132fbd54e2e36207ba679dc9d91bceb0",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2505.21710",
      "published": "2025-05-27T19:53:12Z",
      "updated": "2026-10-13T23:22:23Z",
      "revision": 2,
      "metadata_sha256": "d707797e545402059b43e56a286f479fa51548016e329590baa0c42b11f5e3a3",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2505.13771",
      "published": "2025-05-19T23:12:25Z",
      "updated": "2026-10-14T07:23:09Z",
      "revision": 2,
      "metadata_sha256": "151a043e242167260941faf01c67982d8781d6515c3eb11058cbde3738c12b4d",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2505.13546",
      "published": "2025-05-19T03:28:33Z",
      "updated": "2026-10-13T18:09:51Z",
      "revision": 2,
      "metadata_sha256": "6a8f0897876705b11378820aeb98aaa05c88a9eee8b6afd62bf5ee587707f0a7",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2506.06297",
      "published": "2025-05-17T17:51:23Z",
      "updated": "2026-10-13T18:13:30Z",
      "revision": 2,
      "metadata_sha256": "a4ca3df0d72b92848582f8b3fe87e6254245fe47c85aa683d633f8f2fbccfc9e",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2505.12010",
      "published": "2025-05-17T14:04:20Z",
      "updated": "2026-10-14T09:30:50Z",
      "revision": 5,
      "metadata_sha256": "4c6cfa558241489dc35a336dad86b0632478b78425558371233ed5e9c69aa3e1",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2504.07170",
      "published": "2025-04-09T18:00:00Z",
      "updated": "2026-10-13T18:48:52Z",
      "revision": 3,
      "metadata_sha256": "ee2ca5886282dd56ab5f2696996cb92ea734ebce54934a3fd67d70f2e353af6a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2502.11680",
      "published": "2025-02-17T11:13:39Z",
      "updated": "2026-10-14T09:09:19Z",
      "revision": 2,
      "metadata_sha256": "d63812e6871204beedf2a64c47b13467fdc84694fd3b3236732ea112d57562cc",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2501.05559",
      "published": "2025-01-09T20:11:08Z",
      "updated": "2026-10-14T01:34:00Z",
      "revision": 2,
      "metadata_sha256": "b7d1c607de092d995afbd76fc482cc1e5f5536069324b0941bd49c8271a65906",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2412.08016",
      "published": "2024-12-11T01:54:29Z",
      "updated": "2026-10-14T02:24:55Z",
      "revision": 3,
      "metadata_sha256": "4c2195e1f6c90faf854f6b1d4992e2625950695befaaff04078d7d00de4c3d18",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2410.19371",
      "published": "2024-10-25T08:18:49Z",
      "updated": "2026-10-14T13:35:20Z",
      "revision": 4,
      "metadata_sha256": "c9d3f67e78e63f612f46f4649267135eec6e18a95d66b58bdc0723c17e810323",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2404.01867",
      "published": "2024-04-02T11:44:37Z",
      "updated": "2026-10-14T08:48:10Z",
      "revision": 3,
      "metadata_sha256": "8ace116d075ae7246fc16e430d198e970a6537caf5d36e9fc168b7d3eb82902a",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2402.05203",
      "published": "2024-02-07T19:15:33Z",
      "updated": "2026-10-14T16:26:28Z",
      "revision": 3,
      "metadata_sha256": "f3f2525d22b6e94893248463d0c7625c2411509d53fd9f33e6a89803ecb2bdcb",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2311.04902",
      "published": "2023-11-08T18:59:54Z",
      "updated": "2026-10-14T08:28:09Z",
      "revision": 3,
      "metadata_sha256": "6bad77f5f3ccdd46de643813f26e55f0877e3705bb45899ad287e1db03edb583",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2310.12765",
      "published": "2023-10-19T14:10:09Z",
      "updated": "2026-10-14T07:19:31Z",
      "revision": 2,
      "metadata_sha256": "bf29c53d4c6606d7ba04998e93c8a869c22406a35f255b5e84e876308874d229",
      "repository_status": "new",
      "matched_queries": []
    },
    {
      "arxiv_id": "2112.09646",
      "published": "2021-12-17T17:39:59Z",
      "updated": "2026-10-14T13:25:46Z",
      "revision": 2,
      "metadata_sha256": "cfe0f822f43307868c9251678b3636ee3c04a3c66098486e38b8c8367d4bfcbd",
      "repository_status": "new",
      "matched_queries": []
    }
  ],
  "arxiv_transport": {
    "coverage_complete": true,
    "transport_complete": true,
    "query_count": 11,
    "capped_queries": 0,
    "failed_queries": 0,
    "cache_fallback_pages": 0,
    "queries": [
      {
        "query": "language model post training",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "32463cbd216336e8df2b389e93cb4c8fb5fed17eca64d359b24fff0b8779ccb6",
        "next_offset": 437,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 9,
        "resumed": false,
        "error": null
      },
      {
        "query": "language model preference optimization",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "ca8c7650480c3382c05c4e08d70205507f21c7f299ec585ad2276e369d45e6bd",
        "next_offset": 114,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 3,
        "resumed": false,
        "error": null
      },
      {
        "query": "reinforcement learning language model",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "161e7fea92e50a55963f60db04e8fd16148e5079fb377807a0024862fc327fa3",
        "next_offset": 521,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 11,
        "resumed": false,
        "error": null
      },
      {
        "query": "on policy distillation language model",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "8da3afc17a5ce2a367b018701a5306042d1cb3b6043d884d3a356331909f79be",
        "next_offset": 189,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 4,
        "resumed": false,
        "error": null
      },
      {
        "query": "language model reward model",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "58d73fce01d978962f83a295f7940628bbad83e6e4e0cf7366e95a81c1d4bf67",
        "next_offset": 541,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 11,
        "resumed": false,
        "error": null
      },
      {
        "query": "language model process reward",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "f4109aadbac671387c4f695b931f74d3dfb751ede4f91b7d34f25a8e508c0c0e",
        "next_offset": 70,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 2,
        "resumed": false,
        "error": null
      },
      {
        "query": "test time reinforcement learning",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "2e8e0eaf95e02138b17f6e552bc9e03da605ce212e05b7399b41c00066741d2c",
        "next_offset": 84,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 2,
        "resumed": false,
        "error": null
      },
      {
        "query": "online policy distillation",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "edf8a961164aecce175c21ccae3d7dc8e274747d4b17f1893d9e932710e7d66c",
        "next_offset": 24,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 1,
        "resumed": false,
        "error": null
      },
      {
        "query": "OPD",
        "categories": [
          "cs.CL",
          "cs.LG",
          "cs.CV"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "85c785b7dd1eec0a69f614fa266a3d9c5585ab53e994bea49d7dd9cb3c2e47bb",
        "next_offset": 145,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 3,
        "resumed": false,
        "error": null
      },
      {
        "query": "RLVR GRPO PPO",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "any",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "c818bfa2894672b895ed58bdf04750921465e7e867988e4676328a29ccc274ec",
        "next_offset": 406,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 9,
        "resumed": false,
        "error": null
      },
      {
        "query": "LLM policy",
        "categories": [
          "cs.CL",
          "cs.LG"
        ],
        "match": "all",
        "page_size": 50,
        "maximum_results": 2000,
        "date_from": "None",
        "date_to": "None",
        "identifier_months": [
          "2609",
          "2610"
        ],
        "scan_id": "a28dbda8951444b787943e0dc1241a58",
        "fingerprint": "e4475f76e74d4a4e41d63bc429be5f0724a4e00d6237905519cb413851c63673",
        "next_offset": 414,
        "state": "exhausted",
        "coverage_complete": true,
        "transport_complete": true,
        "cache_fallback_pages": 0,
        "pages": 9,
        "resumed": false,
        "error": null
      }
    ],
    "scope": "configured arXiv API query matrix only; candidate date/identifier-month filtering is separate",
    "review_complete": false,
    "watermark_eligible": false,
    "note": "API retrieval coverage does not certify full-text review or all-source coverage; no review watermark is advanced automatically"
  },
  "derived_from": {
    "run_url": "https://github.com/daiwk/auto-research/actions/runs/38689269736",
    "artifact_name": "post-training-paper-candidates",
    "source_filename": "paper-late-index-post-training.json",
    "source_sha256": "391fd97454189a7b7b25435849f51aea6c06b1c2dd103f8edcc1bee61c2cf407",
    "source_requested_window": {
      "start": "2026-10-01",
      "end": "2026-10-15"
    },
    "source_effective_window": {
      "start": "2026-09-30",
      "end": "2026-10-15"
    },
    "original_candidate_count": 2114,
    "original_coverage_complete": true,
    "original_capped_queries": 0,
    "actual_query_bounds_preserved": true,
    "query_replacements": [],
    "filter": "Keep October canonical IDs OR first publication/source publication in 2026-10-12..15; preserve late-index older original dates. Exhausted containing searches prove subset recall, not new narrower network requests.",
    "excluded_from_previous_month_or_external_historical": 1011
  },
  "review_evidence_notice": "Transport derivation only. Decisions must be independently recorded in this closure's register.",
  "candidate_payload_scope": "Compact identity/date/revision/query fingerprints; abstracts/authors remain in original Actions artifacts identified by derived_from source SHA, not duplicated here."
}
