AI 有眼睛没身体：最强模型在真实身体任务上成功率仅 16.8%
我们总以为 AI 缺的是「看懂世界」，这篇告诉你它缺的是「知道自己身体在哪」。研究者造了个测试：让大模型通过一个真实物理身体去完成找东西、走过去、拿起来这类任务，但把「走路会不会摔」这类低级动作问题全部剥离，只考它每一步的决策。结果九个最强模型全军覆没，最好的成功率也只有 16.8%。而且它们不是认不出目标，是彻底忘了自己：不知道自己走到哪了、有没有撞到东西。这不是你明天能用上的东西，但它划了一条线：AI 的聪明目前只活在屏幕里，一旦要它用身体，它连自己有几只手都不知道。
📄 原文摘要(英文)
Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision with motor control. When a task fails, it is hard to tell whether the VLM made a bad choice or the motor controller simply failed to execute it, e.g., losing balance and falling. In this work, we introduce HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution. At every step, a harnessed, off-the-shelf VLM issues an atomic skill command, and the command is translated into a sub-second chunk of continuous full-body motion with real physical consequences, including gravity and collisions. The body can therefore act freely in the physical world, while execution-side disturbances, balance and motor errors, are factored out. What remains measurable is the model's action intelligence: its moment-to-moment choice of what the body should execute next. Based on this framework, we build HumanCLAW-Bench: 1,218 long-horizon, egocentric find-navigate-interact episodes across 41 indoor scenes. We test nine state-of-the-art VLMs and find that none solves the benchmark; the best model reaches only a 16.8% success rate. Recognizing the target is not the bottleneck. What current VLMs lack is embodied self-awareness: they lose track of their own body, failing to tell where it is, whether it has reached the goal, or whether it has hit an obstacle.