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

arXiv: https://arxiv.org/abs/2605.24050 · HTML: https://mlsanity.com/paper/2605.24050/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 21 May 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 15 of 15)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023)
- [SoK: Agentic Skills -- Beyond Tool Use in LLM Agents](https://mlsanity.com/paper/2602.20867/) (2026)
- [Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward](https://mlsanity.com/paper/2602.12430/) (2026)
- [ToolGen: Unified Tool Retrieval and Calling via Generation](https://mlsanity.com/paper/2410.03439/) (2024)
- [How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings](https://mlsanity.com/paper/2604.04323/) (2026)
- [SkillReducer: Optimizing LLM Agent Skills for Token Efficiency](https://mlsanity.com/paper/2603.29919/) (2026)
- [RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.03275/) (2025)
- [AutoTool: Efficient Tool Selection for Large Language Model Agents](https://mlsanity.com/paper/2511.14650/) (2025)

## Built on by (most cited first, 12 of 12)

- [SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior](https://mlsanity.com/paper/2606.11543/) (2026)
- [Field-Aware Agent Skill Retrieval](https://mlsanity.com/paper/2608.02880/) (2026)
- [From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Based LLM Agents](https://mlsanity.com/paper/2608.09168/) (2026)
- [Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees](https://mlsanity.com/paper/2608.19993/) (2026)
- [AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery](https://mlsanity.com/paper/2609.15820/) (2026)
- [SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents](https://mlsanity.com/paper/2608.18852/) (2026)
- [What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Review](https://mlsanity.com/paper/2609.33153/) (2026)
- [Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance](https://mlsanity.com/paper/2609.05677/) (2026)
- [SkillVine: Agent Skill Evolution via Branching Exploration](https://mlsanity.com/paper/2609.32731/) (2026)
- [SkillFM: Generating Skills for LLM Agents via Latent Flow Matching](https://mlsanity.com/paper/2609.39382/) (2026)
- [Mining Agent Skills from Production Traces](https://mlsanity.com/paper/2610.05777/) (2026)
- [One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents](https://mlsanity.com/paper/2610.11647/) (2026)

## Abstract (arXiv)

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 work, we formulate this performance degradation as the pass rate drop between loading a library of known-helpful skills and the full library. Moreover, we propose to decompose the pass rate drop by conditioning on the skill(s) invocation -- which skills the agent selects during a trajectory -- into two effects: skill shadowing, where the agent selects wrong skills more often as the library expands, and context overhead, where the enlarged context degrades execution even when selection is correct. We derive upper bounds on both effects to characterize their magnitudes of impacts to the pass rate drop. Our empirical estimates of the effects and their upper bounds both show that the skill shadowing effect grows with library size and significantly contributes to the performance degradation, whereas the context overhead effect remains small and indistinguishable from zero. This observed asymmetry establishes that the skill selection failure, not the enlarged context, is the primary bottleneck when expanding the skill libraries.