机器人界的“高考”来了：AI 操控一难就崩
现在的机器人 AI 大多在“开卷考试”里拿高分：固定场景、固定动作，换个位置、多几步就露馅。这篇论文造了一套“闭卷难题”——把空间关系（比如“把杯子放到盘子左边”这种精细指令）和长流程任务（比如“先拿 A 再放 B 最后按 C”）拆成 280 个难度递增的变体，让主流模型去考。结果很直接：空间一复杂、步骤一多，成功率就崩，而且模型不是“差一点”，是根本不知道下一步该干嘛。它不是你明天能用的产品，但它给了行业一个诚实的标尺：现在的机器人 AI，离“看懂世界、连贯做事”还差得远。
📄 原文摘要(英文)
Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However, existing datasets and benchmarks mainly evaluate task completion under predefined settings, offering limited insight into model reasoning under increasing spatial and procedural complexity. We introduce RoboSPA (Robot Spatial-Procedural Assessment), a large-scale robotic manipulation dataset and benchmark for diagnosing embodied reasoning in VLA models. RoboSPA focuses on two core dimensions, Fine-Grained Spatial Reasoning and Long-Horizon Procedural Planning, covering 10 task categories and 56 base tasks. Each task is instantiated across five difficulty levels, yielding 280 variants with increasing spatial ambiguity and procedural complexity. We collect 527K trajectories across multiple embodiments and diverse scenes. Beyond binary success rate, RoboSPA introduces diagnostic metrics for more detailed evaluation. Experiments on representative VLA models show that current systems still struggle with complex spatial relations, precise low-level execution, and memory-intensive planning. These results establish RoboSPA as a challenging diagnostic benchmark for developing more capable, reliable, and generalizable embodied agents. Our data and code are available at https://github.com/fanzhenxuan/RoboSPA.