# Agent skill learning and evolution Area: [LLM agents and tool use](https://mlsanity.com/agents/index.md). HTML: https://mlsanity.com/agents/agent-skill-learning-and-evolution/ ## Key facts - Agent skill learning and evolution: 259 papers on arXiv since 2024 (data through 14 Oct 2026). - 87 of its 259 mapped papers (34%) cite “SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks” (2026, arXiv 2602.12670). - 65 of its 259 mapped papers (25%) cite “SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning” (2026, arXiv 2602.08234). - 80 new papers 17 Sep–14 Oct. ## Most cited here - [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026), cited by 87 papers here - [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026), cited by 65 papers here - [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026), cited by 46 papers here - [Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward](https://mlsanity.com/paper/2602.12430/) (2026), cited by 38 papers here - [SoK: Agentic Skills -- Beyond Tool Use in LLM Agents](https://mlsanity.com/paper/2602.20867/) (2026), cited by 38 papers here - [CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification](https://mlsanity.com/paper/2604.01687/) (2026), cited by 38 papers here - [Reinforcement Learning for Self-Improving Agent with Skill Library](https://mlsanity.com/paper/2512.17102/) (2025), cited by 37 papers here - [How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings](https://mlsanity.com/paper/2604.04323/) (2026), cited by 35 papers here - [EvoSkill: Automated Skill Discovery for Multi-Agent Systems](https://mlsanity.com/paper/2603.02766/) (2026), cited by 34 papers here - [Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale](https://mlsanity.com/paper/2603.02176/) (2026), cited by 32 papers here ## New (17 Sep–14 Oct) - [CausalEvo: Causal Skill Self-Evolution for Health LLM Agents](https://mlsanity.com/paper/2610.21016/) (2026-10-14) - [SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills](https://mlsanity.com/paper/2610.20926/) (2026-10-14) - [When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents](https://mlsanity.com/paper/2610.19910/) (2026-10-14) - [Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach](https://mlsanity.com/paper/2610.19425/) (2026-10-14) - [Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale](https://mlsanity.com/paper/2610.18522/) (2026-10-13) - [Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills](https://mlsanity.com/paper/2610.17860/) (2026-10-13) - [SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models](https://mlsanity.com/paper/2610.17727/) (2026-10-13) - [Embodied Skill Bench: Benchmarking How Well Agents with Embodied Skills Perform on Physical Tasks](https://mlsanity.com/paper/2610.16238/) (2026-10-12) - [When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization](https://mlsanity.com/paper/2610.15492/) (2026-10-11) - [SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents](https://mlsanity.com/paper/2610.15481/) (2026-10-11) - [EnactOpt: Diagnosis-Guided Harness Evolution for Embodied Agents](https://mlsanity.com/paper/2610.14977/) (2026-10-10) - [SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition](https://mlsanity.com/paper/2610.14966/) (2026-10-10) - [StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill](https://mlsanity.com/paper/2610.14601/) (2026-10-10) - [Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress](https://mlsanity.com/paper/2610.14146/) (2026-10-09) - [ClawLoop: Self-Improving Agents via Harness-Native Training Loop](https://mlsanity.com/paper/2610.14118/) (2026-10-09) - [ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills](https://mlsanity.com/paper/2610.12403/) (2026-10-08) - [Trajectory-Guided Fault Localization for Agent Skill Evolution](https://mlsanity.com/paper/2610.11858/) (2026-10-08) - [TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation](https://mlsanity.com/paper/2610.11678/) (2026-10-08) - [RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes](https://mlsanity.com/paper/2610.11480/) (2026-10-08) - [Tracing the Thoughts of a Coding Agent Playing ARC-AGI-3: Lessons for Continual Learning](https://mlsanity.com/paper/2610.11450/) (2026-10-08) - [Skill-SLM: Agent Skill-driven Small Language Models for Reliable Robot Operation](https://mlsanity.com/paper/2610.10812/) (2026-10-07) - [Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models](https://mlsanity.com/paper/2610.10478/) (2026-10-07) - [UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy](https://mlsanity.com/paper/2610.10164/) (2026-10-07) - [Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents](https://mlsanity.com/paper/2610.09856/) (2026-10-07) - [SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles](https://mlsanity.com/paper/2610.09832/) (2026-10-07) - [Goldsmith: Gold-Loss-Guided Definition Optimization with an Agentic Annotation Harness](https://mlsanity.com/paper/2610.09489/) (2026-10-07) - [An Empirical Study of Agent Skills' Downstream Utility](https://mlsanity.com/paper/2610.08875/) (2026-10-06) - [Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?](https://mlsanity.com/paper/2610.08215/) (2026-10-06) - [DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks](https://mlsanity.com/paper/2610.08048/) (2026-10-06) - [SkillPoison: Progressive Skill Poisoning via Successful Experiences](https://mlsanity.com/paper/2610.07645/) (2026-10-06)