Overview

Robot skill learning asks how machines can acquire reusable behaviors—such as grasping, insertion, locomotion, and tool use—and apply them in new situations. Common approaches include imitation learning from robot or human demonstrations, reinforcement learning in simulation and on hardware, and learned motion primitives or diffusion and vision-language-action policies. Researchers organize behaviors into skill libraries, hierarchies, or programs so robots can compose them for longer tasks, while using tactile feedback, language, and human corrections to adapt execution. A central challenge is making skills transfer reliably across objects, scenes, and robot bodies without losing earlier abilities; success on individual skills still does not guarantee robust long-horizon composition.

Latest papers

CardsList

341 papers24 papers in the last four weeks, down 51% on the four weeks before. 0.2% of all new papers.

  1. Demonstration-Free Skill Composition for Navigation and Manipulation

    Nov 19, 2026Madeleine Nouri, Gelareh Mohammadi, Francisco CruzReinforcement LearningRobot Skill Learning

  2. Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation

    Nov 17, 2026Daehee Lee, Dongsu Lee, Sanghyun Ahn +2Robot Policy AdaptationRobot Skill Learning

  3. MARS: Dynamic Routing of Reinforcement-Learned Atomic Skills for Multi-Stage Robotic Manipulation

    Nov 14, 2026Zequan Zeng, Junqin Yang, Kai WangRobotic ManipulationMulti-Task Robotic Manipulation

  4. SPIRE: Task-agnostic embodied continual learning through autonomous situation inference and causal motor-primitive reuse

    Nov 10, 2026Yiyang Jia, Mingyang Lyu, Gongce Cao +3Continual Robot LearningRobot Skill Learning

  5. Flip Anything with Agentic Robotics Self-Learning

    Nov 9, 2026Shuangyu Xie, Kaiyuan Chen, Ken GoldbergRobot Skill LearningDynamic Robotic Manipulation

  6. ReSkill: Selective Self-Improvement for Robot Manipulation

    Nov 7, 2026Zheng Sun, Zhihao Li, Zhuo Li +3Robot Skill LearningSelf-Improving Agents

  7. A Controlled Study of Models, Skills, Feedback, and Curriculum in Agentic Robotics

    Nov 6, 2026Kaiyuan Chen, Xinyue Zhu, Shuangyu Xie +7Agentic AI for RoboticsCoding Agents

  8. PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World

    Nov 4, 2026Qiang Wang, Jianxin Bi, Shulong Jiang +7Robot Skill LearningCode Generation for Robotics

  9. Playing Soccer Like Humans Do: Learning Versatile and Agile Humanoid Soccer via Latent Motion Priors

    Nov 4, 2026Haoyu Shao, Yunshen Wang, Jingze Zhang +5Robot Skill LearningHumanoid Robot Control

  10. Generalizable robotic manipulation through compositional skill reuse

    Oct 31, 2026Hao Ren, Shuohan Chen, Senyuan Mu +3Generalization in Robotic ManipulationRobot Skill Learning

  11. Teach, Abstract, Apply: A Framework for Dialogue-Driven Task Learning with Collaborative Robots

    Oct 30, 2026Chalamalasetti Kranti, Sherzod Hakimov, David SchlangenRobot LearningRobot Skill Learning

  12. META-Robot: Self-Cognition and Capability Scaling in Agentic Robots

    Oct 30, 2026Xuanzhi Feng, Zeyu Liu, Weiheng Gao +11Agentic AI for RoboticsLLM Agent Self-Improvement

  13. Scaling Trusted Autonomy: Towards Generally Capable Verifiable Robots

    Oct 30, 2026Benedict QuarteyNeuro-Symbolic PlanningLanguage-Conditioned Robot Planning

  14. BioAgent: Self-Directed Skill Acquisition and Capability Growth for Long-Horizon Laboratory Protocols

    Oct 30, 2026Gaojing Zhang, Changwen Chen, Zichen Luo +4Robotic Laboratory AutomationRobotics

  15. RoboAtom: Large-scale Atomic-Action Supervision for Robot Learning

    Oct 29, 2026Xueyuan Wei, Xuanxu Wang, Xudong Li +10Robot Manipulation DatasetsRobot Skill Learning

  16. CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization

    Oct 28, 2026Zhiyuan Xiang, Xiang Deng, Wanjie Tao +3Robot Policy LearningRobot Skill Learning

  17. METATRON: A Promptable Whole-Body Execution Layer for Humanoids

    Oct 27, 2026Chen Tessler, Yifeng Jiang, Alec Otto +4Humanoid Robot ControlRobot Motion Generation

  18. Agentic World Action Models

    Oct 21, 2026Zhuoyang Liu, Dantong Niu, Botong Zhang +15Agentic AI for RoboticsWorld Action Models

  19. Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking

    Oct 20, 2026Yuxuan Kuang, Jiashun Wang, Yixuan Sun +5Robot Skill LearningRobotic Manipulation

  20. Data-Efficient Learning from Demonstration for Humanoid Robots via Feature-Level Perception and Prompt-Based Object Detection

    Oct 19, 2026Keyhan Rayati, AliReza Beigy, Anoosheh Saadati +4Robot Skill LearningLearning from Demonstration

  21. Validation of Human Motor Development Scales with Humanoid Robots

    Oct 19, 2026Fanxing Meng, Jing XiaoRoboticsRobot Skill Learning

  22. Compile Once, Run Cheap: Frozen, Portable Skills for Embodied Agents, and What Recursive Self-Improvement Adds

    Oct 18, 2026Jingwen Bai, Guochao Bai, Canbo Zhang +4Robot Skill LearningLLM Agent Self-Improvement

  23. Action-Aligned Latent Planning for Versatile Humanoid Loco-Manipulation

    Oct 17, 2026Yutang Lin, Guanya Shi, C. Karen LiuHumanoid Loco-ManipulationLatent-Space Planning

  24. Solving a Giant Rubik's Cube with a Quadruped Robot

    Oct 17, 2026Lukas Amiet, Gabriel Sánchez-Blanco Repgen, Mayank Mittal +4Robotic ManipulationArticulated Object Manipulation