Metraipolis › archive › dc_ec70323ff931

SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents — arXiv:2608.13173

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13173
License (as archived)
CC0-1.0
Archived
2026-10-19T04:17:34.640Z
SHA-256 of the archived text
5fe3f2044342f0f28967d01b66cb557ecd4253f27567c09989a62f5c887bc884
Stable URL of this page
https://metraipolis.com/documento/dc_ec70323ff931

How to cite

SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents — arXiv:2608.13173 — arXiv (en), https://arxiv.org/abs/2608.13173 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec70323ff931 (Metraipolis archive dc_ec70323ff931, sha256 5fe3f2044342f0f28967d01b66cb557ecd4253f27567c09989a62f5c887bc884)
BibTeX
@misc{dcec70323ff931,
  title = {SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents — arXiv:2608.13173},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13173},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec70323ff931; sha256 5fe3f2044342f0f28967d01b66cb557ecd4253f27567c09989a62f5c887bc884},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13173. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Existing agent skills are primarily created through human manual crafting or agent execution traces, with limited understanding of how each step contributes to overall skill performance on specific tasks; i.e., there remains an open problem in quantifying the contribution of individual steps within an agent skill. To address this issue, we first model skill-step attribution as a Shapley value-based contribution estimation problem, and then propose SkillShapley, a step-level attribution framework for agent skills. Notably, SkillShapley operates in two phases, motivated by key empirical insights, i.e., discretized benchmark rewards that create sharp performance cliffs, and step interactions that are largely additive rather than synergistic. Specifically, it first identifies informative coalitional regions, and then adaptively samples new coalitions that can yield reusable marginal evidence. Experiments on skills from the widely adopted SkillsBench demonstrate that our SkillShapley can effectively and efficiently identify high- or low-value skill steps, providing several key takeaways for agent skill creation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.13173 — 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 2026-10-19T04:13:06.588Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).