uni-robot-agent推动开放权重模型控制机器人
清华大学与 UC Berkeley 的研究人员推出开源框架 uni-robot-agent，通过工具调用将通用大语言模型连接到机器人系统，且无需修改模型权重。论文称，Qwen3.8-Flash-Next 在无特权输入的情况下取得 31.39 的 RoboDojo 分数，高于已发表的 GPT-6 Astra 28.97 分，并在19项真实任务中具有竞争力。相关数据来自论文作者和 Qwen 开发者的报告，尚未得到独立验证。
该框架旨在让研究人员更容易训练、部署和研究开放权重的机器人使用智能体，减少对前沿专有模型的依赖。
Computer Science > Robotics
arXiv:2611.01560 (cs)
[Submitted on 1 Nov 2026]
Title:Democratizing Robot-Use Agents: A Unified Harness with Open Models
Authors:Jiarui 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
View a PDF of the paper titled Democratizing Robot-Use Agents: A Unified Harness with Open Models, by Jiarui Yuan and 27 other authors
#uni-robot-agent#Qwen3.8-Flash-Next#GPT-6 Astra#RoboDojo#π0.5#Dream-1#Tsinghua University#UC Berkeley