开源模型首次在机器人操控上反超闭源
机器人操控的AI一直有个尴尬：能干活的是闭源大模型，但研究者想改进它却碰不到内部。这篇把门槛拆了——一个统一框架，让开源模型直接驱动机器人，零样本上手。结果：开源模型得分31.39，反超了闭源旗舰的28.97，还在19个真实任务上表现不输。更关键的是，他们发现模型能不能用好机器人，取决于四种通用能力，而不是单一技巧。这不是你明天能用的产品，但对机器人研究来说，它把「谁都能改进」这件事变成了现实。
📄 原文摘要(英文)
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.