开源权重 Qwen 借助 uni-robot-agent 统一框架，在 RoboDojo 上取得 31.39 分、25.00% 成功率，超过已公布的 GPT-6 Astra–RoboProbe 配置（28.97 分、22.48%），且不使用特权模拟器输入。
With uni-robot-agent, open-weight Qwen shows robot-use capabilities comparable to the published Astra–RoboProbe results on RoboDojo. The unified harness lays the groundwork for generalizable agentic training.
📄 https://modelscope.ai/papers/2611.01560
🏆 Stronger robot use: Qwen3.8-Flash-Next achieves 31.39 Score / 25.00% success without privileged simulator inputs, versus 28.97 / 22.48% for the published GPT-6 Astra–RoboProbe configuration.
🤖 Physical-robot validation: Across 19 tasks, zero-shot Qwen scores 49.50/100, outscoring both π₀.₅ (47.75, fine-tuned on 10 hours of demonstrations per task) and Dream-1 (35.50, evaluated zero-shot). The agent uses depth; both baselines use RGB only.
🛠️ Unified for generalizable agentic training: Shared motion, perception, skill, and episode interfaces make trajectories across environments and robot embodiments easier to combine for future training.
🧠 What to train next: Analysis identifies visual understanding, spatial grounding, geometric coding, and embodied reasoning as joint priorities for future training.
‼️ Can Qwen directly control the robot as well as GPT-6 Astra? 🚀 Introducing uni-robot-agent: a unified harness for Robot-Use Agents (RUAs), a first step toward RUA training and local deployment. We tested uni-robot-agent with Qwen3.8-Flash-Next running locally: 1️⃣ On RoboDojo, its score rose from 1.90 to 31.39, surpassing the RoboDojo Team’s score with GPT-6 Astra. 2️⃣ On real-world tasks, it outscored fine-tuned π0.5 by 5.75 points and zero-shot Dream-1 by 10 points. 🧵 [1/7]在 X 查看被引用的帖子
来源：ModelScope · x.com