arxiv:2611.01560

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

Published on Nov 1

· Submitted by

Yuxin Zuo on Nov 3

Upvote

Authors:

Jiarui Yuan ,

Bingxiang He ,

Qixin Xu

Abstract

Uni-robot-agent enables open-weight robot-use agents to surpass proprietary models in zero-shot manipulation and suggests joint development of four core capabilities for future training.

Generated by thinkingmachines/Inkling-Small

Robot-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.

View arXiv page View PDF Project page GitHub 100 Add to collection

Community

yuxinzuo

Paper submitter about 19 hours ago

We introduce uni-robot-agent, a unified harness for robot-use agents with open-weight models, designed to support further training.

Without privileged inputs, out-of-the-box Qwen3.8-Flash-Next achieves a RoboDojo Score of 31.39, exceeding the published GPT-6 Astra–RoboProbe result of 28.97, while also performing competitively on 19 real-world tasks.

Beyond benchmarking, we systematically analyze models across generations, families, and sizes, identifying four general capabilities linked to effective robot use. Our findings suggest that future robot-use agent training should develop these capabilities jointly.