Metraipolis › archive › dc_b10a71cb4d29

SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion — arXiv:2608.15165

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15165
License (as archived)
CC0-1.0
Archived
2026-10-18T17:13:45.982Z
SHA-256 of the archived text
9da37f457f6b2898e00a292918eba024184a68e3ced50da814d5b1a8f471762d
Stable URL of this page
https://metraipolis.com/documento/dc_b10a71cb4d29

How to cite

SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion — arXiv:2608.15165 — arXiv (en), https://arxiv.org/abs/2608.15165 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b10a71cb4d29 (Metraipolis archive dc_b10a71cb4d29, sha256 9da37f457f6b2898e00a292918eba024184a68e3ced50da814d5b1a8f471762d)
BibTeX
@misc{dcb10a71cb4d29,
  title = {SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion — arXiv:2608.15165},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15165},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b10a71cb4d29; sha256 9da37f457f6b2898e00a292918eba024184a68e3ced50da814d5b1a8f471762d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15165. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents can continually improve without parameter updates by converting historical experience into reusable procedural knowledge. However, existing methods often consolidate experience based on semantic similarity or LLM judgments, which may merge superficially related but behaviorally incompatible strategies and thereby degrade performance. To address the issue, we propose SkillCommit, an online skill evolution framework that continuously transforms experience into a hierarchical library of reusable skills. Rather than generalizing from individual experiences immediately, SkillCommit first preserves each experience as an instance-specific patch, retaining its locally validated behavior. As patches accumulate, SkillCommit abstracts those sharing a common behavioral mechanism into higher-level skills. Specifically, for each incoming skill, embedding-based retrieval first identifies candidate related skills. Cross-instance replay and an LLM-based mechanism check determine whether these skills transfer across cases and share a common underlying mechanism. Candidates that pass both checks are abstracted into a higher-level skill and committed only if it preserves the validated behavior of all constituent skills. Experiments on RuleArena, OpenExempt and KOR-Bench demonstrate that SkillCommit consistently improves agent performance across diverse domains. Moreover, the learned skills transfer across model scales and families, enabling cross-model experience transfer.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15165 — 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 2026-10-18T16:29:13.778Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).