cs.RONov 11, 2026

JustRUA: A Controlled Study of GPT-6 Robot-Use Agents

Authors: Zefan Wang, Yufan Dang, Xuanwei Shi, Mingqi Gao, Cheng Yin, SikYuen Tam, Hanyu Liu, Yasheng Wang, 

Organizations: Tsinghua University · ModelBest · Huazhong University of Science and Technology · Peking University · 

Abstract

GPT-6 Astra can drive a robot arm directly through a fixed harness, and scores of such robot-use agents on RoboDojo have risen quickly since. Reported systems differ in harness and test subset and often change several designs at once, so it is hard to tell which choices produce the gains. We take these designs apart and test them in one framework, along the harness around the model, the action interface, the reuse of experience and the scene geometry given to the model. A lean harness that keeps the full episode history and stops each motion early goes a long way. Reusing experience changes how the model acts but is not a free lunch, and scene geometry helps most, even when depth is predicted from RGB alone. JustRUA starts from the official L3 harness and keeps only what matters most. Even with no learned policy, self-improvement loop or task-specific tuning, this simple harness raises the score on the RoboDojo simulation benchmark substantially, from 29.7 to 50.3.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Democratizing Robot-Use Agents: A Unified Harness with Open Models

    Nov 1, 2026Jiarui Yuan, Yuxin Zuo, Xiaoyu Huang +25Robotic Tool UseEmbodied Agent Benchmarks

  2. An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond

    Sep 21, 2026Wenbo Zhang, Kaixuan Wang, Yutao Ouyang +9Language-Conditioned Robot ManipulationGeneralization in Robotic Manipulation