Metraipolis › archive › dc_90e35519bd9b

FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training — arXiv:2610.00385

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00385
License (as archived)
CC0-1.0
Archived
2026-10-06T12:09:08.575Z
SHA-256 of the archived text
c5de8ec290be891d4ae565be3a7f91eb2d0521c1a4877f8e058426e219cb2ee2
Stable URL of this page
https://metraipolis.com/documento/dc_90e35519bd9b

How to cite

FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training — arXiv:2610.00385 — arXiv (en), https://arxiv.org/abs/2610.00385 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90e35519bd9b (Metraipolis archive dc_90e35519bd9b, sha256 c5de8ec290be891d4ae565be3a7f91eb2d0521c1a4877f8e058426e219cb2ee2)
BibTeX
@misc{dc90e35519bd9b,
  title = {FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training — arXiv:2610.00385},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00385},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90e35519bd9b; sha256 c5de8ec290be891d4ae565be3a7f91eb2d0521c1a4877f8e058426e219cb2ee2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00385. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Replay selectors often rank cached trajectories by format feedback, confidence, freshness, or response length, although cache-level correctness and downstream learner utility are distinct objectives. We formalize this selection-to-learning gap and introduce FAER as an auditable full-trajectory replay framework. Its training-free fixed selector is a protocol baseline; FAER-UTILITY is the learner-aware selector fitted on disjoint calibration blocks. The normalized gradient alignment is reported as a baseline, while a disposable optimizer-aware virtual update supplies a magnitude-aware utility surface. The audit contract freezes observed fields and replay traces before evaluation labels are joined. On GSM8K with Qwen2.5-1.5B-Instruct, the matched learner study reports quality 0.6329 for the fixed selector, compared with 0.5482 for uniform and 0.6037 for format-feedback under 128 updates. Metadata-only cross-fitted calibration reaches $0.6476\!\pm\!0.0139$ over eight seeds (median 0.6481; paired 95% interval $[+0.079,+0.122]$) at 63,276 target-run tokens; its recorded full cost is 189,642 tokens and 3.48 GPU-hours including calibration. The completed FAER-UTILITY row reaches 0.6624 at 62,844 target-run tokens and 4.26 GPU-hours. Format-feedback selects records with correctness 0.6953, compared with 0.3594 for the fixed selector, despite the different downstream ranking. The completed comparison surfaces report the learner-aware ablation, same-seed gap, policy-optimization rows, and strict zero-shot transfer.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.00385 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T10:21:28.058Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).