mlsanityData to 14 Oct 2026

SkillNet: Create, Evaluate, and Connect AI Skills

arXiv 2603.04448 ↗First posted 26 Feb 2026cs.AI cs.CL cs.CVcited by 53

Not on the map. Why?

Cited by 38 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To address this challenge, we introduce SkillNet, an open infrastructure for creating, evaluating, and organizing AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 600,000 skills, an interactive platform, and a versatile Python toolkit. Experiments on ALFWorld, WebShop, and ScienceWorld show 40% higher average rewards and 30% fewer execution steps across multiple backbone models. Furthermore, SkillNet-Gym benchmarks skill retrieval, utilization, and composition, while SkillNet-Fabric enables task-specific skill routing through lightweight Wikis. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 36 of its 76 references that are in the map. First posted on arXiv 26 Feb 2026.

Builds on

36 of 76 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  5. 2023A Survey of Large Language Modelscited by 2,576
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  9. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  10. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,251
  11. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  12. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
24 more
  1. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  2. 2020Knowledge Graphscited by 621
  3. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 587
  4. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  5. 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 431
  6. 2024Agent Workflow Memorycited by 383
  7. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 327
  8. 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Taskscited by 315
  9. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 289
  10. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 278
  11. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 197
  12. 2025SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skillscited by 192
  13. 2021KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extractioncited by 180
  14. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 109
  15. 2026Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scalecited by 105
  16. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 100
  17. 2026Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionalitycited by 72
  18. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 49
  19. 2026CL-bench: A Benchmark for Context Learningcited by 47
  20. 2016A Survey of Symbolic Execution Techniquescited by 36
  21. 2026When Single-Agent with Skills Replace Multi-Agent Systems and When They Failcited by 35
  22. 2025PolySkill: Learning Generalizable Skills Through Polymorphic Abstractioncited by 27
  23. 2025SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinementcited by 9
  24. 2026Skill-Based Autonomous Agents for Material Creep Database Constructioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 53.

53 papers.

Sort:

By area:

  1. 2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalizationcited by 94
  2. 2026SkillClaw: Let Skills Evolve Collectively with Agentic Evolvercited by 81
  3. 2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skillscited by 55
  4. 2026SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Taskscited by 55
  5. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 49
  6. 2026SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agentscited by 25
  7. 2026GEMS: Agent-Native Multimodal Generation with Memory and Skillscited by 21
  8. 2026From Context to Skills: Can Language Models Learn from Context Skillfully?cited by 19
  9. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 18
  10. 2026SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolutioncited by 18
  11. 2026From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skillscited by 16
  12. 2026SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scalecited by 16
38 more
  1. 2026OpenSkill: Open-World Self-Evolution for LLM Agentscited by 12
  2. 2026SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinementcited by 12
  3. 2026WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolutioncited by 12
  4. 2026Group of Skills: Group-Structured Skill Retrieval for Agent Skill Librariescited by 11
  5. 2026Skill-Use: Can LLMs Actually Use Skills in Agentic Harnesses?cited by 10
  6. 2026SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topologycited by 9
  7. 2026HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolutioncited by 9
  8. 2026Not All Skills Help: Measuring and Repairing Agent Knowledgecited by 6
  9. 2026Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Librariescited by 6
  10. 2026Red Skills or Blue Skills? A Dive Into Skills Published on ClawHubcited by 5
  11. 2026Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysiscited by 5
  12. 2026From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agentscited by 5
  13. 2026Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectoriescited by 4
  14. 2026RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agentscited by 3
  15. 2026Unsupervised Skill Discovery for Agentic Data Analysiscited by 2
  16. 2026Hierarchical Experimentalist Agentscited by 2
  17. 2026SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agentscited by 2
  18. 2026Coalition-Aware Skill Reliability for Self-Evolving Agentscited by 2
  19. 2026MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skillscited by 1
  20. 2026Evidence Over Plans: Online Trajectory Verification for Skill Distillationcited by 1
  21. 2026Workflow Closure Is Not Scientific Closure in Auto-Research Systemscited by 1
  22. 2026Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoningcited by 1
  23. 2026Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agentscited by 1
  24. 2026Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skillscited by 1
  25. 2026FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skillscited by 1
  26. 2026HiSkill: Empowering LLM Agents with Hierarchical Skill Graphscited by 1
  27. 2026SkillTrace: Traversing a Query-Skill Graph for Composable LLM Agentscited by 1
  28. 2026MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graphcited by 1
  29. 2026COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimizationcited by 1
  30. 2026RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agentscited by 1
  31. 2026Pomona: Continuous Code Quality Improvement via Small, Agentic Pull Requests at Bloombergcited by 0
  32. 2026Process-Reward Tactic Evolution for Long-Horizon Bioinformatics Workflowscited by 0
  33. 2026Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safetycited by 0
  34. 2026SkillMentor: LLM Agent Self-Evolution via Learning Blind-Spot Diagnosiscited by 0
  35. 2026OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolutioncited by 0
  36. 2026TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generationcited by 0
  37. 2026SPT: Skills as Pre-Training Data for Agentic Language Modelscited by 0
  38. 2026Demystifying Agent Skills for Smart Contract Auditing: Design, Effectiveness, Behavioral Impactcited by 0

50 most cited of 53 All 53 (JSON)