Tsinghua & Berkeley open-source uni-robot-agent: Qwen beats GPT-6 zero-shot
Jiarui Yuan · hf · 2026-11-03
Tsinghua University and UC Berkeley released uni-robot-agent, a unified open harness for robot-use agents enabling open-weight models to be further trained. 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. The paper also proposes jointly developing four core capabilities for future RUA training.
More from Embodied
- Stanford CoRL paper adds safety filters to humanoid RL policies with no retraining needed — drmapavone · 2026-11-03
- Huawei's TinyAstral Distills Self-Evolving Harnesses into 4B Robot Agents, Wins Across Six Benchmarks — Kehong Gong · 2026-11-03
- Reviewer: The $2000+ Duo Is Fun but Hard to Recommend as Your Only Phone — film_girl · 2026-11-03
- General-purpose LLM with robot arm beats specialized robot models: Kohane — zakkohane · 2026-11-03
- Zhiyui runs 6 robots for 24 hours straight in a convenience store; Google douses space datacenter hype — 创业邦 · 2026-11-03
- Apps still not optimized for iPhone Duo's dual screen weeks after launch — evielync · 2026-11-03