cs.RONov 7, 2026

ReSkill: Selective Self-Improvement for Robot Manipulation

Authors: Zheng Sun, Zhihao Li, Zhuo Li, Wenrui Liu, Xin Wang, Fei Chen

Organizations: The Chinese University of Hong Kong, Hong Kong SAR, China · Openmind Intelligent Robot Co., Ltd., Wuhu, China

Abstract

Self-improvement on compositional manipulation tasks requires deciding what to reuse, where to improve, and which changes to retain. We present ReSkill, a selective self-improvement framework that concentrates revision on capability gaps. A coding agent constructs an object-centric task graph from an instruction and a skill library, then uses node-level execution records to locate failures. At the task level, it revises stage organization, hand-off conditions, and recovery routes; at the skill level, it strengthens perception, motion, manipulation, and verification capabilities that repeatedly fail. Candidate revisions undergo full-task evaluation and paired comparisons before adoption, allowing local changes to accumulate into validated skills and an independently executable policy. The agent participates only during development; the deployed policy calls the retained skills without invoking the agent at run time. On the same development set, average success across ten RoboDojo tasks rises from 30.0% for the initial versions to 86.2% for the final adopted programs; retained programs achieve 83.6% in recorded robustness and model-selection evaluations. Across eight real-world tasks, ReSkill succeeds in 72 of 80 rebuilt-simulation trials and 62 of 80 real-robot trials (77.5%). The median revision changes only three functions, approximately 0.5% of a program, while 39% of task-specific functions in later-added tasks directly reuse existing implementations. These results show how locating local deficiencies, validating candidate changes, and accumulating reusable skills can improve execution of compositional manipulation tasks.

Figures & tables

Explore similar work

CardsList
  1. Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents

    Oct 1, 2026Yen-Jen Wang, Haozhe Jiang, Shuying Deng +7Robot Skill LearningLarge Language Model-Based Robot Planning

  2. Learning to Compose: Recursive Self-Improvement of Shared Executable Stacks for Zero-Shot Long-Horizon Robot Manipulation

    Oct 17, 2026Yangzhi Chen, Feiran Liu, Zishuo Wang +4Robotic ManipulationRecursive Self-Improvement