SkillAlchemy：开放世界智能体技能创建
SkillAlchemy: Open-World Agent Skill Creation
浏览论文内容
中文总结 AI 辅助
SkillAlchemy是一个以准入为中心的基于源的开放世界智能体技能创建框架，在87个SkillsBench v1.1任务上，其技能通过率较无技能执行提升19.9个百分点、较最强自动化基线提升8.6个百分点，性能接近人工策划技能。
中文摘要 AI 辅助
智能体技能是可复用的过程性产物，用于在推理时为语言智能体扩展专门的工作流、工具规范和领域行为。然而，创建可靠技能仍在很大程度上依赖人类创作、模型先验或执行轨迹。对于不熟悉的任务，这些来源往往不可用，因此需要从开放世界材料中创建技能。本文研究开放世界技能创建：给定一个未明确说明的技能简介和一个源访问规范，创建者必须发现简介遗漏的与行为相关的需求，并确定每个源自源的过程的合理范围。我们提出SkillAlchemy，一个以准入为中心的基于源的技能创建框架。SkillAlchemy通过对比证据识别隐式需求，基于证据支持的范围接纳候选过程，并将接纳的内容编译为语法引导的技能包。在87个SkillsBench v1.1任务上进行的大量实验表明，SkillAlchemy相比无技能执行将通过率提高了19.9个百分点，相比最强的自动化基线提高了8.6个百分点，同时达到了与人工策划技能相当的性能。
英文摘要
Agent skills are reusable procedural artifacts that extend language agents with specialized workflows, tool conventions, and domain behaviors at inference time. However, creating reliable skills still depends largely on human authorship, model priors, or execution traces. These sources are often unavailable for unfamiliar tasks, suggesting the need to create skills from open-world materials. In this paper, we study open-world skill creation: given an underspecified skill brief and a source-access specification, a creator must discover behavior-relevant requirements omitted by the brief and determine how broadly each source-derived procedure is justified. We propose SkillAlchemy, an admission-centered framework for source-grounded skill creation. SkillAlchemy identifies implicit requirements through contrastive evidence, admits candidate procedures based on evidence-supported scope, and compiles the admitted content into a grammar-guided skill package. Extensive experiments across 87 SkillsBench v1.1 tasks demonstrate that SkillAlchemy improves pass rate over no-skill execution by 19.9 percentage points and the strongest automated baseline by 8.6 percentage points, while achieving performance comparable to human-curated skills.
