Metraipolis › archive › dc_3276ff8b85da

Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL — arXiv:2610.23048

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23048
License (as archived)
CC0-1.0
Archived
2026-10-19T08:42:25.521Z
SHA-256 of the archived text
8fcc78ce8c4b572ca4b1407d4a527eb78918524482ee32e6d84b3cb0fa82e76a
Stable URL of this page
https://metraipolis.com/documento/dc_3276ff8b85da

How to cite

Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL — arXiv:2610.23048 — arXiv (en), https://arxiv.org/abs/2610.23048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3276ff8b85da (Metraipolis archive dc_3276ff8b85da, sha256 8fcc78ce8c4b572ca4b1407d4a527eb78918524482ee32e6d84b3cb0fa82e76a)
BibTeX
@misc{dc3276ff8b85da,
  title = {Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL — arXiv:2610.23048},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23048},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3276ff8b85da; sha256 8fcc78ce8c4b572ca4b1407d4a527eb78918524482ee32e6d84b3cb0fa82e76a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon interaction requires agents to make multiple decisions in a changing environment. Outcome-based GRPO lacks fine-grained guidance for intermediate decisions. Recent methods distill completed trajectories into reusable skills and use hindsight-conditioned OPD to provide dense token-level credit. However, skill-induced probability shifts do not necessarily represent reward-aligned credit; especially after an erroneous action changes subsequent interaction states, skill-conditioned supervision may become mismatched with the current state. To address this mismatch, we propose \methodname{}, which routes two complementary hindsight skills according to trajectory outcomes and error boundaries: Positive skills capture successful workflows to reinforce successful trajectories and pre-error decisions, while Negative skills capture failure-specific corrections to target decisive errors. The post-error suffix is optimized exclusively by GRPO, retaining outcome-based learning without extending potentially mismatched hindsight supervision. Extensive experiments demonstrate competitive task performance and support effective fine-grained credit allocation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.23048 — 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 2026-10-19T08:39:10.057Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).