# SkillEvolver: Skill Learning as a Meta-Skill

arXiv: https://arxiv.org/abs/2605.10500 · HTML: https://mlsanity.com/paper/2605.10500/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 26 of 26)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward](https://mlsanity.com/paper/2602.12430/) (2026)
- [Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale](https://mlsanity.com/paper/2603.02176/) (2026)

## Built on by (most cited first, 16 of 16)

- [SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing](https://mlsanity.com/paper/2606.14239/) (2026)
- [Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.28424/) (2026)
- [Hypothesis-Driven Skill Optimization for LLM Agents](https://mlsanity.com/paper/2606.22330/) (2026)
- [FederatedSkill: Federated Learning for Agentic Skill Evolution](https://mlsanity.com/paper/2606.03143/) (2026)
- [Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories](https://mlsanity.com/paper/2607.25560/) (2026)
- [SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown](https://mlsanity.com/paper/2610.04008/) (2026)
- [SkillHEX: Improving Agent Skills via Hypothesis-Driven Autonomous Exploration and Exploitation](https://mlsanity.com/paper/2608.05628/) (2026)
- [Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents](https://mlsanity.com/paper/2608.09555/) (2026)
- [From Execution to Capability: Scientific Experience Consolidation via Procedural Knowledge Synthesis](https://mlsanity.com/paper/2607.24459/) (2026)
- [Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators](https://mlsanity.com/paper/2608.02712/) (2026)
- [SkillAlchemy: Open-World Agent Skill Creation](https://mlsanity.com/paper/2608.23417/) (2026)
- [CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution](https://mlsanity.com/paper/2609.04865/) (2026)
- [EVISKILL: Grounding Skill Evolution in Replayable Evidence](https://mlsanity.com/paper/2610.05030/) (2026)
- [Mining Agent Skills from Production Traces](https://mlsanity.com/paper/2610.05777/) (2026)
- [Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents](https://mlsanity.com/paper/2610.07979/) (2026)
- [Trajectory-Guided Fault Localization for Agent Skill Evolution](https://mlsanity.com/paper/2610.11858/) (2026)

## Abstract (arXiv)

Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose SkillEvolver, a lightweight, plug-and-play solution for online skill learning, in which a single meta-skill iteratively authors, deploys, and refines domain-specific skills. The learning target of SkillEvolver is the skill's prose and code, not model weights, so that the resulting artifact drops into any agent without retraining; and the meta-skill itself is just another skill, loaded through the same interface by any protocol-compliant CLI-agent. Unlike trace-distillation, the meta-skill refines only after deploying the learnt skill, such that the learning signal comes from failures another agent encounters while using it -- not from exploratory traces alone. Refinement iterations are governed by a fresh-agent overfit audit that catches possible leakage as well as deployed-skill-specific failures, including the silent-bypass mode in which a skill appears valid in content but is never invoked at runtime. On 83 SkillsBench tasks spanning 15+ domains, SkillEvolver reaches 56.8% accuracy versus 43.6% for curated human skills and 29.9% for the no-skill baseline; on three GPU kernel optimization tasks from KernelBench, it also raises mean speedup from 1.16 to 1.51 on average.