SkillAlign：面向基于大语言模型智能体的技能接口对齐
SkillAlign: Aligning Skill Interfaces for LLM-based Agents
浏览论文内容
中文总结 AI 辅助
提出SkillAlign框架，通过多视角程序卡片和多种暴露接口对齐技能呈现方式，证明暴露形式显著影响任务成功率，应优化技能呈现而非仅选择技能。
中文摘要 AI 辅助
语言模型智能体日益依赖技能：即用于推理、工具使用和交互的可复用程序性知识。现有工作研究技能如何获取、检索、压缩或组合，但通常假设一旦选定技能，其与智能体的接口是固定的。我们认为这忽视了技能效用的一个关键来源：同一技能根据其暴露方式的不同，可能有所帮助、分散注意力或产生误导。我们提出SkillAlign，一个与提供者无关的框架，将候选技能表示为多视角程序卡片，并通过替代暴露接口进行渲染，包括完整指令、提示、压缩摘要、工作流或不予暴露。这实现了反事实评估，其中任务、智能体和候选技能固定，仅暴露接口变化。在ALFWorld和SkillsBench上，我们表明暴露形式显著影响任务成功率和渲染上下文成本，且紧凑的top-k暴露可以优于全库注入。我们进一步在ALFWorld上进行了基于重放的策略学习分析，表明自适应暴露包含可学习信号，但仍远未达到最优选择。我们的结果表明，技能增强型智能体不仅应优化使用哪些技能，还应优化这些技能的呈现方式。
英文摘要
Language-model agents increasingly rely on skills: reusable procedural knowledge for reasoning, tool use, and interaction. Existing work studies how skills are acquired, retrieved, compressed, or composed, but often assumes that once a skill is selected, its interface to the agent is fixed. We argue that this overlooks a key source of skill utility: the same skill can help, distract, or mislead depending on how it is exposed. We propose SkillAlign, a provider-agnostic framework that represents candidate skills as multi-view procedural cards and renders them through alternative exposure interfaces, including full instructions, hints, compressed summaries, workflows, or no exposure. This enables counterfactual evaluation where the task, agent, and candidate skills are fixed while only the exposure interface varies. Across ALFWorld and SkillsBench, we show that exposure form substantially affects task success and rendered context cost, and that compact top-k exposure can outperform full-library injection. We further conduct a replay-based policy-learning analysis on ALFWorld, showing that adaptive exposure contains learnable signal but remains far from oracle selection. Our results suggest that skill-augmented agents should optimize not only which skills to use, but also how those skills are presented.
发表机构
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。
