给智能体技能的内部单元打分，判断每个部分值不值钱。
What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills
- 基于结构感知的谢尔比估值法，识别技能内各单元依赖关系
- 在4个基准上验证，能准确还原单元间互动并保留整体性能提升
- 适合想安全压缩或优化技能结构的研究者和工程师
智能体技能正通过自动化反馈循环不断优化，生成包含长结构化内容的成果，但其内部单元的价值仍不清晰。本文研究技能估值：在固定智能体和未见任务分布下，为技能内部单位（如规则、示例、脚本、启发式）分配信用。与数据或提示片段估值不同，技能单元具有结构性——彼此依赖、构成文档层级、触发行为、消耗有限上下文。我们提出SkillSV，一种结构感知的谢尔比风格估值框架。SkillSV将技能解析为单元、依赖关系与层级结构，仅评估有效反事实技能。采用成对删除与长度中性填充，分离内容价值与上下文成本，并使用带预算的滚动生成器估计噪声智能体评价结果。在四个智能体基准上评估了SkillSV的忠实性、可操作性与解释性：它能恢复单元间交互，保持整体技能提升，指导安全剪枝与压缩。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。