机器人学常识：用动作答题，暴露AI知识短板
机器人模型学了一堆操作，但常识可能掉光了。研究者设计了一个测试：让机器人通过“把东西放到正确位置”来回答问题，比如“面包通常放在哪里？”——放对才算懂。结果发现，微调后的机器人模型在简单常识上还行，但复杂语义（比如“生日派对需要什么？”）明显不如原始视觉语言模型。好消息是，如果训练时同时保留问答任务，知识保留得更好。这告诉你：别以为机器人会开冰箱门就懂“冰箱里该放牛奶”——它可能只是记住了动作，没理解世界。
📄 原文摘要(英文)
Embodied Vision-Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to answer through action. Each question becomes a short tabletop episode where the agent performs a single object-placement action to select among candidate answers, yielding an action-grounded success rate with reduced control confounds. We curate a test suite of such environments across diverse commonsense and world-knowledge categories and introduce layerwise intent probing to localize answer-relevant information across the VLM backbone and action head. In a large-scale study of 7 VLA models and 9 VLM baselines, we systematically rank models across categories, finding that VLAs show solid performance on simple concepts while exhibiting larger gaps on richer semantic categories relative to their source VLMs, that VQA co-training is associated with better knowledge retention, and that answer-relevant signals peak in middle VLA layers but attenuate in upper layers. Act2Answer is available at https://tttonyalpha.github.io/act2answer/.