AI 能看懂空间，但一动手就露馅
现在的多模态大模型能准确说出物体在哪，但真让它动手操作，成功率只有一半出头。研究者造了个叫 VA-Bench 的测试场：只给 AI 看 RGB 视频演示，不给任何内部坐标或预设轨迹，让它自己选摄像头角度、发笛卡尔坐标指令、根据执行反馈修正。结果很有意思：最强的模型在“描述物体位置”上拿满分，但完整任务三局平均成功率只有 53.9%;让它主动转摄像头比被动看多个视角强得多，成功率从 27.9% 翻倍到 57.5%;一旦遇到没见过的几何布局，成功率直接掉 30 个百分点以上；五步长任务没有一个模型能完整走完。换句话说，AI 的“空间理解”是纸面的——它知道东西在哪，但不知道手该往哪伸。这不是你明天能用上的东西，但它划了一条线：当前 AI 的“看懂”和“做到”之间，还隔着一条真实的鸿沟。
📄 原文摘要(英文)
Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence, interpret it in a common spatial frame, and act on it. We introduce VA-Bench to evaluate the complete observe-reason-act-revise loop. General-purpose MLLMs learn procedural context from RGB-only demonstrations, actively select camera viewpoints, issue metric Cartesian commands, and revise them from execution feedback. Models receive no privileged object poses, oracle trajectories, or learned action heads. A fixed model-agnostic controller executes only model-specified targets. VA-Bench contains 14 base task families (11 single-arm and three dual-arm), seven held-out geometry/layout variants, and a long-horizon five-object composition track. We evaluate 12 primary model conditions in three independent runs over the same 20 physically verified seeds per base task, reporting terminal success, nine trajectory-level behavioral diagnostics, and subtask progress. First, the best-performing model scores 100.0% on target localization and 78.9% on spatial relations in the annotated run. Its three-run macro-average task success is only 53.93+/-3.17%. Second, active camera control significantly improves task success over passive multi-view observation. In one matched comparison, success rises from 27.86% to 57.50%. Third, held-out geometric transfer can reduce task success by over 30 percentage points. No model completes a strict long-horizon episode, despite substantial partial progress. VA-Bench thus tests whether general-purpose MLLMs can turn visual demonstrations and actively acquired evidence into successful embodied action.