VagueBench shows embodied agents fail when context disappears
Embodied agents can misread otherwise sufficient instructions when ordinary contextual cues are removed, creating a robustness and safety gap for robots operating in homes and other open-world settings. VagueBench tests this with 1,303 instruction pairs in the AI2-THOR simulator, covering missing entities, procedures, constraints, and prior knowledge. Across six agents, task success fell 19.65% relatively and empty plans rose 54.10%; the paper reports the problem also persists on real robots.