titleDemocratizing Robot-Use Agents: A Unified Harness with Open Models
authorsJiarui Yuan, Yuxin Zuo, Xiaoyu Huang, Wenbo Zhang, Kwanyoung Park, Junlin Yang, Tianxiang Zhang, Ruoqu Chen, Yutao Ouyang, Bingxiang He, Xingtai Lv, Hongjin Wu, Jiajun Liu, Jiahao Zhao, Tianwei Luo, Haozhan Li, Cheng Qian, Jiaxin Ge, Huan-ang Gao, Kaisen Yang, Jiaqi Deng, Qixin Xu, Siqiao Huang, Bowen Zhou, Mengdi Xu, Zhiyuan Liu, Pieter Abbeel, Ning Ding
date2026-11-01
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.01560
upvotes42 (Hugging Face Daily Papers, 2026-11-04)
linksabs pdf hf code
cite
abstractRobot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary models limits research into further training. To democratize RUA research, we introduce uni-robot-agent, a unified harness for competitive open-weight robot use that supports further training. Without privileged inputs, an out-of-the-box Qwen3.8-Flash-Next achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and many VLA/WAM baselines, and performs competitively on 19 real-world tasks. Our analysis across model generations, families, and sizes links effective robot use to four general capabilities, suggesting that future RUA training should develop them jointly.

bibtex

@misc{yuan2026democratizing,
  title={Democratizing Robot-Use Agents: A Unified Harness with Open Models},
  author={Jiarui Yuan and Yuxin Zuo and Xiaoyu Huang and Wenbo Zhang and Kwanyoung Park and Junlin Yang and Tianxiang Zhang and Ruoqu Chen and Yutao Ouyang and Bingxiang He and Xingtai Lv and Hongjin Wu and Jiajun Liu and Jiahao Zhao and Tianwei Luo and Haozhan Li and Cheng Qian and Jiaxin Ge and Huan-ang Gao and Kaisen Yang and Jiaqi Deng and Qixin Xu and Siqiao Huang and Bowen Zhou and Mengdi Xu and Zhiyuan Liu and Pieter Abbeel and Ning Ding},
  year={2026},
  eprint={2611.01560},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.01560}
}