cs.RONov 9, 2026

RoboACE: Adversarial Co-Evolution for Robot Self-Improvement

Authors: Delin Zhao, Zhengrong Yue, Junlin He, Yali Wang

Abstract

Robot agents can improve reusable skills, planning procedures, and recovery strategies from execution feedback, yet a fixed practice source leaves the search for new weaknesses unchanged. Useful practice depends on the agent's current capabilities, so the procedure that chooses practice must also be revisable. We present RoboACE (Robot Adversarial Co-Evolution), a framework that jointly evolves curriculum and execution harnesses around frozen foundation models. The curriculum harness uses accumulated capability evidence to propose informative challenges, while the execution harness responds with reusable revisions that expand execution capabilities. Alternating updates hold one side fixed as the other changes, and admitted challenges form fixed snapshots for comparing execution revisions. Starting from a compact set of LIBERO practice conditions, the resulting frozen deployment outperforms the evaluated controllers and agent systems across four LIBERO-family panels. On LIBERO-PRO, it reaches 74.0% success, exceeding the initial deployment by 15.0 percentage points and direct execution by its VLA controller by 13.5 points. Case studies document changes to evidence-guided practice selection, drawer-skill grounding, and controller intervention.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SEAR: Self-Evolving Agentic Robotics

    Oct 13, 2026Xinyi Wang, Bangzheng Li, Hanyu Wang +5Agentic AI for RoboticsRobot Learning

  2. EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution

    Oct 7, 2026Python Song, Zhixuan Liang, Kelsey Fu +3Continual Robot LearningRobot Skill Learning