Metraipolis › archive › dc_3e32eee55f9f
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents — arXiv:2610.07979
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07979
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:19:19.896Z
- SHA-256 of the archived text
6a3201730006c9e128603538058b1ee1d318bdd7fd269f6002fd3f4098230f9a- Stable URL of this page
https://metraipolis.com/documento/dc_3e32eee55f9f
How to cite
Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents — arXiv:2610.07979 — arXiv (en), https://arxiv.org/abs/2610.07979 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3e32eee55f9f (Metraipolis archive dc_3e32eee55f9f, sha256 6a3201730006c9e128603538058b1ee1d318bdd7fd269f6002fd3f4098230f9a)
BibTeX
@misc{dc3e32eee55f9f,
title = {Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents — arXiv:2610.07979},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07979},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3e32eee55f9f; sha256 6a3201730006c9e128603538058b1ee1d318bdd7fd269f6002fd3f4098230f9a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07979. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As agents continuously improve by generating and revising Skills, the process that discovers and refines those Skills becomes a learnable object in its own right. Task-Skills directly act on task execution, whereas Meta-Skills govern how agents discover and improve future Skills; their value therefore emerges through the subsequent search processes they induce. Existing approaches improve Meta-Skills from observed raw Skill-search trajectories and branch outcomes. However, branch performance entangles the effects of the initial discovery state and the Meta-Skill revision that generated the search process, making it difficult to characterize what a particular revision actually changed, and pushing updates toward revisions that benefit from favorable states rather than those that improve the process. We introduce HMED (Hindsight Meta-Experience Distillation), a mechanism for constructing Meta-Experience for self-improving agents. HMED revisits the completed event from which a revision originates and re-executes the incumbent and revised Meta-Skills from the same restored discovery state, so that the changes associated with the revision can be observed under a shared condition. Each comparison is distilled into a Meta-Experience, a structured record that can be reused by future updates, so that even revisions that are not ultimately retained still contribute a learning signal. Across three interactive agent benchmarks and both open-source and closed-source models, HMED consistently improves Skill discovery performance over strong baselines, shifting Meta-Skill learning beyond branch outcomes toward the consequences of changing the improvement process. 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/2610.07979 — 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 2026-10-07T11:15:24.573Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).