cs.RO · 2611.00978 Copy arXiv ID · Oct 31, 2026 Save Generalizable robotic manipulation through compositional skill reuse Authors: Hao Ren , Shuohan Chen , Senyuan Mu , Ruihan Huang , Wanfeng Shang , Yajing Shen
Organizations: Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China · HKUST Shenzhen Research Institute, The Hong Kong University of Science and Technology, Shenzhen, China · School of Artificial Intelligence, Shenzhen University,Shenzhen, China · National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China
In Abstract Hao Ren, Shuohan Chen, Senyuan Mu, Ruihan Huang, Wanfeng Shang, Yajing Shen
More in this topic Generalization in robotic manipulation studies how robots transfer grasping and interaction skills to new objects, scenes, tasks, and embodiments.
See all 379 papers → Also in May 2, 2026 · Xitie Zhang, Aming Wu, Yahong Han ICL for Robotics Zero-Shot Robotic Manipulation
School of Artificial Intelligence, College of Intelligence and Computing, Tianjin University, China · School of Computer Science and Information Engineering, Hefei University of Technology, China
Nov 7, 2026 · Zheng Sun, Zhihao Li, Zhuo Li +3 Robot Skill Learning Self-Improving Agents
The Chinese University of Hong Kong, Hong Kong SAR, China · Openmind Intelligent Robot Co., Ltd., Wuhu, China
Oct 11, 2026 · Xupeng Zhang, Yantai Yang, Chang Guo +2 Generalization in Robotic Manipulation Long-Horizon Robotic Manipulation
AutoLab, School of Artificial Intelligence, Shanghai Jiao Tong University
May 2, 2026 J/K move · Enter open · S save
Xitie Zhang, Aming Wu, Yahong Han
School of Artificial Intelligence, College of Intelligence and Computing, Tianjin University, China · School of Computer Science and Information Engineering, Hefei University of Technology, China
Cross-task generalization is a core challenge in open-world robotic manipulation, and the key lies in extracting transferable manipulation knowledge from seen tasks. Recent in-context learning approaches leverage seen task demonstrations to generate actions for unseen tasks without parameter updates. However, existing methods provide only low-level continuous action sequences as context, failing to capture composable skill knowledge and causing models to degenerate into superficial trajectory imitation. We propose Decompose and Recompose, a skill reasoning framework using atomic skill-action pairs as intermediate representations. Our approach decomposes seen demonstrations into interpretable skill--action alignments, enabling the model to recompose these skills for unseen tasks through compositional reasoning. Specifically, we construct a task-adaptive dynamic demonstration library via visual-semantic retrieval combined with skill sequences from a planning agent, complemented by a coverage-aware static library to fill missing skill patterns. Together, these yield skill-comprehensive demonstrations that explicitly elicit compositional reasoning for skill composition and execution ordering. Experiments on the AGNOSTOS benchmark and real-world environments validate our method's zero-shot cross-task generalization capability.