What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills
arXiv AIArchived Aug 06, 2026✓ Full text saved
arXiv:2608.04562v1 Announce Type: new Abstract: 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 unit
Full text archived locally
✦ AI Summary· Claude Sonnet
Computer Science > Artificial Intelligence
[Submitted on 5 Aug 2026]
What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills
Tao Li, Junfeng Liu, Qinghua Zhao, Yifan Li, Lei Wang, Bo Shao, Xuejun Liu, Linjun Shou
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.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2608.04562 [cs.AI]
(or arXiv:2608.04562v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.04562
Focus to learn more
Submission history
From: Junfeng Liu [view email]
[v1] Wed, 5 Aug 2026 07:56:26 UTC (1,896 KB)
Access Paper:
HTML (experimental)
view license
Current browse context:
cs.AI
< prev | next >
new | recent | 2026-08
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Export BibTeX Citation
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Demos
Related Papers
About arXivLabs
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)