技能组：面向智能体技能库的分组结构技能检索
Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
AI总结：
本文提出GoSkills，一种分组结构技能检索方法，通过构建基于类型技能图的锚点中心技能组，提升智能体在有限技能预算下对可见需求的覆盖能力，改进了传统技能检索方法的性能。
摘要：
增强技能的智能体越来越多地依赖大型可重用技能库，但检索相关技能不同于提供可使用的上下文。现有方法通常返回原子技能或依赖感知的捆绑，其内部角色仍隐含，使智能体需自行推断执行入口点、支持技能、可见需求和故障规避指导。我们引入技能组（GoSkills），一种推理时的分组结构检索方法，将智能体面对的检索对象从扁平技能列表转变为紧凑、角色标注的执行上下文。GoSkills从类型技能图构建锚点中心技能组，通过组图扩展支持组，将选定的组计划瓶颈为有限的原子技能负载，并渲染具有Start、Support、Check和Avoid字段的固定执行合同，不改变下游智能体、技能负载或执行环境。在SkillsBench和ALFWorld上的实验表明，GoSkills在有限技能预算下保持可见需求覆盖，优于扁平技能访问基线，并在相对结构检索参考中经常提升奖励和智能体单独运行时间。
英文摘要：
Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically return atomic skills or dependency-aware bundles whose internal roles remain implicit, leaving the agent to infer the execution entry point, support skills, visible requirements, and failure-avoidance guidance. We introduce Group of Skills (GoSkills), an inference-time group-structured retrieval method that changes the agent-facing retrieval object from a flat skill list to a compact, role-labeled execution context. GoSkills builds anchor-centered skill groups from a typed skill graph, expands support groups through a group graph, bottlenecks the selected group plan into a bounded set of atomic skill payloads, and renders a fixed execution contract with Start, Support, Check, and Avoid fields, without changing the downstream agent, skill payloads, or execution environment. Experiments on SkillsBench and ALFWorld show that GoSkills preserves visible-requirement coverage under a small skill budget, improves over flat skill-access baselines, and often improves reward and agent-only runtime relative to structural retrieval references.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
