mlsanityData to 7 Oct 2026

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

arXiv 2604.01687 ↗First posted 2 Apr 2026cs.AIcited by 117

On the map: LLM agents and tool use → Agent skill learning and evolution

also in 1 more
Abstract (arXiv)

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts. Currently, skill generation is not only label-intensive due to manual authoring, but also may suffer from human--machine cognitive misalignment, which can lead to degraded agent performance, as evidenced by evaluations on SkillsBench. Therefore, we aim to enable agents to autonomously generate skills. However, existing self-evolving methods designed for tools cannot be directly applied to skills due to their increased complexity. To address these issues, we propose CoEvoSkills, a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages. Specifically, CoEvoSkills couples a Skill Generator that iteratively refines skills with a Surrogate Verifier that co-evolves to provide informative and actionable feedback without access to ground-truth test content. On SkillsBench, CoEvoSkills outperforms five baselines on both Claude Code and Codex, and generalizes strongly to six additional LLMs. The code is publicly available at https://github.com/Zhang-Henry/CoEvoSkills.

Key facts. Cited by 117 papers in the map (data through 7 Oct 2026). Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use. Builds on 26 of its 34 references that are in the map. First posted on arXiv 2 Apr 2026.

Builds on

26 of 34 references.

Closest ancestors · 6

Same direction, newest first

  1. 2026SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?28 Feb
  2. 2026SoK: Agentic Skills -- Beyond Tool Use in LLM Agents24 Feb
  3. 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks13 Feb
  4. 2026Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward12 Feb
  5. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning9 Feb
  6. 2025Reinforcement Learning for Self-Improving Agent with Skill Library18 Dec

Other references · 20

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  5. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  6. 2025OpenAI GPT-5 System Cardcited by 910
  7. 2026Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfacescited by 515
  8. 2024Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agentscited by 341
  9. 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 105
  10. 2025Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?cited by 91
  11. 2025SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experiencecited by 68
  12. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
8 more
  1. 2025EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systemscited by 34
  2. 2025LLM-Based Human-Agent Collaboration and Interaction Systems: A Surveycited by 28
  3. 2026Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoningcited by 12
  4. 2026When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigationcited by 12
  5. 2025QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generationcited by 10
  6. 2025Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safetycited by 6
  7. 2024UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrieverscited by 5
  8. 2026Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Taskscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 117.

117 papers.

Sort:

By area:

  1. 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skillscited by 122
  2. 2026SkillGen: Verified Inference-Time Agent Skill Synthesiscited by 29
  3. 2026SkillGrad: Optimizing Agent Skills Like Gradient Descentcited by 23
  4. 2026SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revisioncited by 21
  5. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agentscited by 19
  6. 2026From Context to Skills: Can Language Models Learn from Context Skillfully?cited by 19
  7. 2026SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolutioncited by 18
  8. 2026From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skillscited by 18
  9. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 17
  10. 2026SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineeringcited by 14
  11. 2026MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolutioncited by 12
  12. 2026SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditingcited by 11
38 more
  1. 2026Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?cited by 11
  2. 2026SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectoriescited by 10
  3. 2026OpenSkill: Open-World Self-Evolution for LLM Agentscited by 9
  4. 2026Dream-RSI: Recursive Self-Improvement through Evolving Worldscited by 9
  5. 2026SkillMaster: Toward Autonomous Skill Mastery in LLM Agentscited by 8
  6. 2026AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompterscited by 7
  7. 2026Poise: Position-Aware One-Instruction Skill Injection for Silent Execution on LLM Agentscited by 7
  8. 2026SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Usecited by 7
  9. 2026Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remembercited by 7
  10. 2026WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolutioncited by 7
  11. 2026SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agentscited by 6
  12. 2026SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestrationcited by 6
  13. 2026CODESKILL: Learning Self-Evolving Skills for Coding Agentscited by 6
  14. 2026Skill Is Not Document: Query-Conditioned Compatibility for LLM Agent Skill Routingcited by 6
  15. 2026Agent Skill Evaluation and Evolution: Frameworks and Benchmarkscited by 6
  16. 2026Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Librariescited by 6
  17. 2026Harnessing AtomisticSkills for Agentic Atomistic Researchcited by 5
  18. 2026Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learningcited by 5
  19. 2026VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generationcited by 5
  20. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 5
  21. 2026SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agentscited by 5
  22. 2026From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skillscited by 5
  23. 2026RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environmentscited by 5
  24. 2026ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillationcited by 4
  25. 2026SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systemscited by 4
  26. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  27. 2026SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent Systemcited by 3
  28. 2026SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skillscited by 3
  29. 2026Not All Skills Help: Measuring and Repairing Agent Knowledgecited by 3
  30. 2026Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agentscited by 3
  31. 2026MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architecturescited by 3
  32. 2026MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deductioncited by 2
  33. 2026Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolutioncited by 2
  34. 2026Evolving Ensemble of Agentscited by 2
  35. 2026MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?cited by 2
  36. 2026SkillComposer: Learning to Evolve Agent Skills for Specification and Generalizationcited by 2
  37. 2026Unsupervised Skill Discovery for Agentic Data Analysiscited by 2
  38. 2026OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Modelscited by 2

50 most cited of 117 All 117 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
  2. 2026SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
  3. 2026EvoSkill: Automated Skill Discovery for Multi-Agent Systems
  4. 2026SkillFocus: Evolving Agent Skills via Capability Decomposition
  5. 2026Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
  6. 2026Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
  7. 2026TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
  8. 2026MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation