Event ·Official first-hand

GPT-6 Astra 零微调操控机器人,RoboDojo 42 项任务居首

一篇 arXiv 论文提出 LLM as policy 设定:语言模型不做任务微调直接充当机器人操作策略,在 RoboDojo 全部 42 项任务上评测 3 个 LLM,并与 40 个公开策略对比。GPT-6 Astra 在 2,100 次试验中取得 22.48% 平均成功率和 28.97 Score,排名高于所有公开策略。同样的后处理流程下,GPT-5.5 只有 0.88%,DeepSeek-Flash 为 1.92%。Astra 的能力呈两极分化:语义理解类任务泛化良好,但高精度控制、动态控制和双手协同任务明显落后。one-shot 演示在整体上没有带来收益,部分交互轨迹显示模型能在回合内对扰动做纠正。

Current read

Astra 不微调直接当机器人策略,42 项任务拿下 22.48%,GPT-5.5 只有 0.88%。

11 sources74° AI heatLast updated 2026/9/21 06:39:47

Evidence

11 sources
Primary sourcearXiv: DeepSeek
View source
Related source 3Browser Use
View source
Related source 5shao__meng
View source
Related source 6向阳乔木
View source
Related source 8lmarena.ai
View source
Related source 9Justine Moore
View source
Related source 10eric zakariasson
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.