GPT-6 Astra 零微调操控机器人，RoboDojo 42 项任务居首
An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond
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%。
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。
An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond
Embodied AI systems are often organized into System 1 and System 2. System 1 is typically a pretrained policy that generates actions at high frequency, whereas System 2 is often instantiated as a vision-enabled language model for high-level planning. We ask whether a large language model (LLM) can act as the policy for robot manipulation without task-specific finetuning. We call this setting LLM as policy. We evaluate three LLMs on all 42 RoboDojo tasks and compare their scores with 40 public policies. Astra and GPT-5.5 use the official 50-episode-per-task protocol; DeepSeek-Flash uses 10 episodes per task. GPT-6 Astra achieves 22.48% average success rate and 28.97 Score over 2,100 trials, ranking above every public entry. Yet GPT-5.5 and DeepSeek-Flash reach only 0.88% and 1.92% average success rate with the same post-processing. We find that Astra exhibits a sharply polarized capability profile. It generalizes well to tasks that require semantic understanding but not high-precision control. In contrast, it performs poorly on tasks that require precision, dynamic control, or complex bimanual coordination. In-context experiments show no aggregate benefit from one-shot demonstrations, while selected interaction traces show within-episode corrections under perturbations. Overall, the evaluated LLMs vary substantially in manipulation performance. Astra stands out and provides initial evidence for the potential of a general-purpose manipulation model, although reliable precision and dynamic control remain limitations in the evaluated setting.
