arXiv 2610.185222026-10-14cs.AI

隐式路由中的迷失：大语言模型智能体在规模化加载相关技能时如何失效

Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale

The University of Hong Kong（香港大学）；Huazhong University of Science and Technology（华中科技大学）

Jinlin Liu, Wei Chen, Xiaojin Zhang

备注：: 22 pages, including references and appendices. Code: https://github.com/jinlinll/lost-in-implicit-routing

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该研究发现LLM智能体在规模化添加无关技能时会出现技能路由崩溃，提出显式预选择作为缓解措施，为相关智能体的技能协议和评估提供了依据。

摘要：

可复用技能使大语言模型（LLM）智能体能够按需加载特定任务指令，但这一设计让执行过程依赖于技能元数据上的隐式路由。我们通过固定SkillsBench任务及其黄金技能，同时添加无关技能，测试该设计是否可规模化。我们发现技能路由崩溃现象：即使相关技能仍可用，智能体加载的技能数量越来越少，甚至不加载任何技能。当存在1000个无关技能时，加载技能的召回率从73.6%降至27.4%，零加载率从9.3%升至51.6%，而从同一库中进行显式选择的召回率仍保持73.9%。加载其他技能（包括黄金技能的合理替代项）的情况过于罕见，无法解释这种下降。仅屏蔽无关技能的描述可在很大程度上恢复技能加载，但在元数据完整的情况下，明确要求智能体规划技能使用的召回率仍低于预选择。这些发现表明，当技能选择与任务执行竞争时，描述会产生语义干扰，指令会产生干扰。我们还评估了显式预选择作为一种实用的缓解措施，包括其覆盖范围和延迟权衡。我们的分析为技能库不断增长的智能体的技能协议和评估提供了参考。

英文摘要：

Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We test whether this design scales by holding SkillsBench tasks and their golden skills fixed while adding irrelevant skills. We find skill routing collapse: agents increasingly load fewer or no skills, even though the relevant skills remain available. With 1,000 irrelevant skills, loaded-skill recall falls from 73.6% to 27.4% and the zero-load rate rises from 9.3% to 51.6%, whereas explicit selection from the same library retains 73.9% recall. Loading other skills, including plausible alternatives to golden skills, is too rare to explain this decline. Masking only the descriptions of irrelevant skills largely restores skill loading, yet with the metadata intact, explicitly asking agents to plan skill use still yields lower recall than preselection. These findings point to semantic interference from descriptions and instruction interference when skill choice competes with task execution. We also evaluate explicit preselection as a practical mitigation, including its coverage and latency trade-offs. Our analysis informs skill protocols and evaluation for agents with growing skill libraries.

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。

AI总结：

摘要：

英文摘要：

相关论文