More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries 事件

More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries arXiv:2605.24050v1 Announce Type: cross Abstract: Skill libraries allow LLM agents to load task-specific instructions on demand, letting non-expert users solve domain-specific tasks through natural language without knowing which skills exist or how they work. However, performance degrades as libraries grow -- by up to 21\% when scaling from a small set of helpful skills to a 202-skill library. In this