arXiv cs.AI· Jin Ye, Yifan Jiang, Lan-zhe Guo·· 13 小时前AI 评分38
SkillBrowser：面向可扩展技能智能体的选择性技能暴露框架
SkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents
AI 导读
SkillBrowser 是一个由 Meta-Skill 管理的框架，让 LLM 智能体识别当前能力需求、构造针对性查询并按需选择性加载技能。在六个 SRA-Bench 子集和五个 LLM 上，其聚合准确率优于静态检索和基于 LLM 的选择方法，并缓解了已可解实例上的准确率下降。局限在于有用技能调用不足和额外延迟，收益仍因模型和任务而异。
正文 · 原文
Abstract:Large language model agents increasingly rely on skills to extend their capabilities in complex tasks. However, scalable skill use requires Selective Skill Exposure (SSE): providing relevant procedural content when needed while avoiding unnecessary exposure that may disrupt reasoning. Existing paradigms fall short in complementary ways. Progressive disclosure exposes metadata for a growing skill library, introducing context pollution; retrieval limits catalog exposure, but static retrieval from the initial task query may be misaligned with capability needs that emerge during reasoning and may still inject unnecessary skills. We propose SkillBrowser, a Meta-Skill-managed framework that enables an agent to identify current capability needs, formulate targeted queries, and selectively load skills on demand. Across six SRA-Bench subsets and five LLMs, SkillBrowser improves aggregate accuracy over static retrieval and LLM-based selection, including multi-step tool use, and mitigates accuracy degradation on already-solvable instances. Benefits remain model- and task-dependent, with under-invocation of useful skills and additional latency as key limitations. These results demonstrate the viability of Meta-Skill-managed SSE for scalable skill repositories.
| Comments: | 23 pages, 3 figures. Submitted to ACL Rolling Review, October 2026 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.23554 [cs.AI] |
| (or arXiv:2610.23554v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23554 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jin Ye [view email]
[v1]
Fri, 16 Oct 2026 14:44:01 UTC (1,275 KB)
来源：arXiv cs.AI · arxiv.org