# Not All Skills Help: Measuring and Repairing Agent Knowledge

arXiv: https://arxiv.org/abs/2606.15390 · HTML: https://mlsanity.com/paper/2606.15390/

## Key facts

- Cited by 6 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 22 of its 24 references that are in the map.
- First posted on arXiv 13 Jun 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, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle](https://mlsanity.com/paper/2510.16079/) (2025)
- [CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification](https://mlsanity.com/paper/2604.01687/) (2026)
- [Reinforcement Learning for Self-Improving Agent with Skill Library](https://mlsanity.com/paper/2512.17102/) (2025)
- [SkillClaw: Let Skills Evolve Collectively with Agentic Evolver](https://mlsanity.com/paper/2604.08377/) (2026)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning](https://mlsanity.com/paper/2402.15506/) (2024)
- [SkillNet: Create, Evaluate, and Connect AI Skills](https://mlsanity.com/paper/2603.04448/) (2026)
- [Skill Retrieval Augmentation for Agentic AI](https://mlsanity.com/paper/2604.24594/) (2026)
- [Towards Enterprise-Ready Computer Using Generalist Agent](https://mlsanity.com/paper/2503.01861/) (2025)
- [GraSP: Graph-Structured Skill Compositions for LLM Agents](https://mlsanity.com/paper/2604.17870/) (2026)
- [Leveraging In-Context Learning for Language Model Agents](https://mlsanity.com/paper/2506.13109/) (2025)

## Built on by (most cited first, 6 of 6)

- [Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents](https://mlsanity.com/paper/2609.01245/) (2026)
- [The Right Lesson at the Right Step: Deriving Control Updates for Self-Evolving Agents](https://mlsanity.com/paper/2609.34988/) (2026)
- [EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment](https://mlsanity.com/paper/2609.38661/) (2026)
- [Mining Agent Skills from Production Traces](https://mlsanity.com/paper/2610.05777/) (2026)
- [An Empirical Study of Agent Skills' Downstream Utility](https://mlsanity.com/paper/2610.08875/) (2026)
- [Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules](https://mlsanity.com/paper/2610.14216/) (2026)

## Abstract (arXiv)

LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how to apply them to LLM judgment alone. We argue that this conflates two distinct roles: generating a skill from experience is a creative act that judgment handles well, while deciding whether that skill actually helps requires empirical evidence across many tasks. Measuring per-skill causal contributions via randomized masking, we find that skill libraries exhibit pervasive causal heterogeneity: individual skills routinely help on some task types while hurting on others, yet their opposing effects cancel in aggregate, making them invisible to global curation methods. We propose ASSAY, a framework that separates generation from curation: it computes a per-skill causal attribution on a small development set, restructures the library offline, and suppresses skills with negative predicted effect for each test task. Across seven base models spanning four providers and two benchmarks (AppWorld and tau-bench), ASSAY consistently improves over prior skill-curation approaches. On AppWorld's hardest split, DeepSeek-V3 achieves 69.3% task-goal completion (47.4% relative improvement), a new state of the art among all published methods including weight-tuned approaches. On tau-bench retail, GPT-4.1 improves by 8.7% relative, advancing past o4-mini, o1, and GPT-4.5 on the public leaderboard without any weight modification. Ablation traces the dominant gain to per-task masking, confirming that the bottleneck is matching skills to tasks at inference time, not removing bad skills globally. Code is available at https://github.com/aiming-lab/assay.