Agent Skill Learning

Ask about this topic

Overview

Agent skill learning studies how agents acquire, represent, retrieve, and combine reusable behaviors, from motor primitives in robotics to tool-use procedures in language-model agents. Common approaches include hierarchical reinforcement learning and latent skill discovery, imitation from demonstrations, and external skill libraries refined from successful and failed trajectories using verification or reinforcement learning. Work is tested in settings such as LIBERO and ALFWorld for embodied tasks, WebArena for web use, and benchmarks that measure continual learning and skill transfer. A central challenge is making skills reliable and useful on held-out tasks: more updates or broader libraries can improve coverage but also cause drift, costly retrieval, or unsafe behavior, so evaluation increasingly examines transfer, execution quality, and lifecycle safety.

Latest papers

CardsList

174 papers41 papers in the last four weeks, up 95% on the four weeks before. 0.2% of all new papers.

  1. TRACE: Capability-Targeted Agentic Training

    Apr 7, 2026Hangoo Kang, Tarun Suresh, Jon Saad-Falcon +1LLM Agent Self-ImprovementAgent Skill Learning

    Stanford University

  2. SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources

    Apr 5, 2026Shuaike Shen, Wenduo Cheng, Mingqian Ma +3Agent Skill LearningAI Agents for Scientific Discovery

    Ray and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University · Machine Learning Department, School of Computer Science, Carnegie Mellon University

  3. MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization

    Apr 2, 2026Lisheng Zhang, Lilong Wang, Xiangyu Sun +14Drug DiscoveryAutonomous Research Agents

    Peking University Health Science Center, Peking University, Beijing, China · Shanghai AI Laboratory, Shanghai, China · Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China

  4. From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?

    Apr 2, 2026Binyan Xu, Dong Fang, Haitao Li +1Agent Skill LearningMulti-Agent Orchestration

    The Chinese University of Hong Kong, Hong Kong, China · LIGHTSPEED, Shenzhen, China

  5. PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor

    Apr 1, 2026Yutao Yang, Junsong Li, Qianjun Pan +7Lifelong Learning AgentsAgent Skill Learning

    School of Computer Science and Technology, East China Normal University · Shanghai AI Laboratory · School of Psychology and Cognitive Science, East China Normal University

  6. Dynamic Dual-Granularity Skill Bank for Agentic RL

    Mar 30, 2026Songjun Tu, Chengdong Xu, Qichao Zhang +5LLM Agent Skill LearningAgent Skill Learning

    Institute of Automation, Chinese Academy of Sciences · Pengcheng Laboratory · Sun Yat-Sen University +1

  7. SportSkills: Physical Skill Learning from Sports Instructional Videos

    Mar 26, 2026Kumar Ashutosh, Chi Hsuan Wu, Kristen GraumanSports Video AnalysisVideo Representation Learning

    University of Texas at Austin

  8. STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems

    Mar 22, 2026Alfred Shen, Aaron ShenAgentic AISelf-Evolving Agents

  9. DeEscalWild: A Real-World Benchmark for Automated De-Escalation Training with SLMs

    Mar 20, 2026Md Hasebul Hasan, Krity Haque Charu, Eshwara Prasad Sridhar +2Small Language ModelsAgent Skill Learning

    Department of Computer Science and Engineering, University of Texas at Arlington, USA · Department of Industrial, Manufacturing, and Systems Engineering, University of Texas at Arlington, USA

  10. When AI Agents Learn from Each Other: Insights from Emergent AI Agent Communities on OpenClaw for Human-AI Partnership in Education

    Mar 17, 2026Eason Chen, Ce Guan, Zhonghao Zhao +5AI in EducationMulti-Agent Collaboration

    Carnegie Mellon University, USA · GiveRep Labs, Virgin Islands (British) · Sui Foundation, Cayman Islands

  11. ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning

    Mar 17, 2026Tik Yu Yim, Wenting Tan, Sum Yee Chan +2Domain Adaptation for LLMsAgent Skill Learning

    The University of Hong Kong, Hong Kong SAR, China

  12. ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning

    Mar 17, 2026Yu Li, Rui Miao, Zhengling Qi +1RL for Language Model ReasoningLLM Mathematical Reasoning

    Department of Electrical and Computer Engineering, George Washington University · Department of Mathematical Sciences, University of Texas at Dallas · School of Business, George Washington University

  13. MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents

    Mar 13, 2026Zhengwei Xie, Zhisheng Chen, Ziyan Weng +7Self-Evolving AgentsLong-Horizon Agent Tasks

    USTC · NTU · CityU-DG +4

  14. XSkill: Continual Learning from Experience and Skills in Multimodal Agents

    Mar 12, 2026Guanyu Jiang, Zhaochen Su, Xiaoye Qu +1Agent Skill LearningMultimodal Agents

    Hong Kong University of Science and Technology · Zhejiang University · Huazhong University of Science and Technology

  15. KernelClaw: A Multi-Agent Framework for GPU Kernel Optimization with Dual-Memory Mechanisms

    Mar 10, 2026Qitong Sun, Jun Han, Tianlin Li +6GPU Kernel OptimizationGPU Kernel Generation

    School of Computer Science and Engineering, Beihang University, China · Zhejiang Lab, China · Nanyang Technological University, Singapore

  16. LAR-MoE: Latent-Aligned Routing for Mixture of Experts in Robotic Imitation Learning

    Mar 9, 2026Ariel Rodriguez, Chenpan Li, Lorenzo Mazza +5Robot Imitation LearningAgent Skill Learning

    Department of Translational Surgical Oncology, NCT/UCC Dresden, a partnership between DKFZ, MF UKD, TUD, HZDR Dresden, Germany. · Cluster of Excellence-CeTI, TUD, Germany. · Department of Visceral, Thoracic and Vascular Surgery, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD, Germany.

  17. OSExpert: Computer-Use Agents Learning Professional Skills via Exploration

    Mar 9, 2026Jiateng Liu, Zhenhailong Wang, Rushi Wang +6Computer-Use AgentsAgent Skill Learning

    University of Illinois Urbana-Champaign · Stevens Institute of Technology

  18. Hierarchical Latent Action Model

    Mar 6, 2026Hanjung Kim, Lerrel Pinto, Seon Joo KimLatent Action LearningAgent Skill Learning

    Yonsei University · New York University

  19. EvoSkill: Automated Skill Discovery for Multi-Agent Systems

    Mar 3, 2026Salaheddin Alzubi, Noah Provenzano, Jaydon Bingham +2Agent Skill LearningLLM Agent Self-Improvement

    Sentient · Virginia Tech

  20. SkillNet: Create, Evaluate, and Connect AI Skills

    Feb 26, 2026Yuan Liang, Ruobin Zhong, Haoming Xu +47LLM Agent Skill EvaluationAgent Skill Learning

  21. UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs

    Feb 25, 2026Devan Shah, Owen Yang, Daniel Yang +2RL for Language Model ReasoningReasoning Diversity

    Princeton University

  22. Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning

    Feb 23, 2026Nathan Gavenski, Felipe Meneguzzi, Odinaldo RodriguesImitation LearningAgent Skill Learning

    King’s College London, London, United Kingdom · University of Aberdeen & PUCRS, Aberdeen, United Kingdom

  23. Agent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments

    Feb 18, 2026Yangjie Xu, Lujun Li, Lama Sleem +7Small Language ModelsLLM Agent Skill Retrieval

    University of Luxembourg · Foyer S.A. · Princeton University +1

  24. Evolving Programmatic Skill Networks

    Jan 7, 2026Haochen Shi, Xingdi Yuan, Bang LiuContinual Learning for LLM AgentsLLM-Based Program Synthesis

    DIRO & Institut Courtois, Université de Montréal · Mila – Québec AI Institute · Microsoft Research +1