Metraipolis › archive › dc_25033de3ee4d

Self-Evolving Agents through Privileged Retrospective Distillation — arXiv:2610.27495

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27495
License (as archived)
CC0-1.0
Archived
2026-10-21T07:07:48.131Z
SHA-256 of the archived text
f14261b6e205df401aca9120f83dc104fdb0d91ea8110f8c7196ac17c4989080
Stable URL of this page
https://metraipolis.com/documento/dc_25033de3ee4d

How to cite

Self-Evolving Agents through Privileged Retrospective Distillation — arXiv:2610.27495 — arXiv (en), https://arxiv.org/abs/2610.27495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25033de3ee4d (Metraipolis archive dc_25033de3ee4d, sha256 f14261b6e205df401aca9120f83dc104fdb0d91ea8110f8c7196ac17c4989080)
BibTeX
@misc{dc25033de3ee4d,
  title = {Self-Evolving Agents through Privileged Retrospective Distillation — arXiv:2610.27495},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27495},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25033de3ee4d; sha256 f14261b6e205df401aca9120f83dc104fdb0d91ea8110f8c7196ac17c4989080},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-evolving agents aim to improve from their own experience rather than remain fixed after deployment, but naturally collected trajectories often lack ground-truth solutions or verifier-derived rewards. We introduce Retrospective Self-Distillation (RSD), a multi-round framework that turns such experience into dense supervision using privileged retrospective context. For each on-policy trajectory, the same underlying model acts as both student and teacher: the teacher re-scores the student's realized actions while conditioning on cross-task precedents and lessons, together with turn-level reflection and future hindsight from the completed trajectory. The resulting teacher distribution is distilled back into the policy through on-policy self-distillation. Across rounds, the experience bank grows and the retrospective context is refreshed, allowing the model, its data, and its supervision to co-evolve. We further introduce frontier-guided context-policy evolution, where a stronger frontier model proposes constrained edits to how privileged context is constructed. Across ALFWorld, ScienceWorld, and SearchQA with Qwen3-8B and Qwen3-14B, RSD improves performance by up to 59.7% relative to the base model, while frontier-guided context-policy evolution adds up to a further 44.7% relative improvement over a fixed context policy. These results show that naturally accumulated experience can be converted into persistent model capability without ground-truth trajectories or verifier-derived rewards for the core policy update.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.27495 — 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 2026-10-21T07:05:43.565Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).