Metraipolis › archive › dc_813aca71db6f

What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills — arXiv:2608.04562

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04562
License (as archived)
CC0-1.0
Archived
2026-10-31T11:12:37.158Z
SHA-256 of the archived text
103071b7d78e8ed7b83b23074d9ab146e12a21c0b419b662feec8099c1d0f806
Stable URL of this page
https://metraipolis.com/documento/dc_813aca71db6f

How to cite

What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills — arXiv:2608.04562 — arXiv (en), https://arxiv.org/abs/2608.04562 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_813aca71db6f (Metraipolis archive dc_813aca71db6f, sha256 103071b7d78e8ed7b83b23074d9ab146e12a21c0b419b662feec8099c1d0f806)
BibTeX
@misc{dc813aca71db6f,
  title = {What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills — arXiv:2608.04562},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04562},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_813aca71db6f; sha256 103071b7d78e8ed7b83b23074d9ab146e12a21c0b419b662feec8099c1d0f806},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04562. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agent skills are increasingly optimized by automated feedback loops, producing long structured artifacts whose internal value remains unclear. We study skill valuation: assigning credit to the internal units of a fixed skill, such as rules, examples, scripts, and heuristics, under a fixed agent and held-out task distribution. Skill valuation differs from data or prompt-span valuation because skill units are structured: they may depend on other units, belong to a document hierarchy, trigger agent behavior, and consume limited prompt context. We introduce SkillSV, a structure-aware Shapley-style framework for skill valuation. SkillSV compiles a skill into units, dependencies, and hierarchy, so that only valid counterfactual skills are evaluated. It uses paired deletion and length-neutral padding to separate content value from context cost, and estimates the resulting values with a rollout-budgeted estimator for noisy agent evaluations. On four agentic benchmarks, we assess the faithfulness, actionability, and explanation of SkillSV: it recovers unit interactions, preserves aggregate skill lift, and guides safe pruning and compression.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04562 — 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 2026-10-31T11:02:13.413Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).