Embodied QA

Embodied question answering asks agents to answer questions about environments they observe and move through, often using robots or egocentric video. Common approaches combine vision-language models with active exploration, spatial maps or scene graphs, and episodic or long-term memory to find and retain relevant evidence. Benchmarks such as OpenEQA, HM-EQA, and SQA3D test scene understanding, spatial reasoning, and navigation-linked answering, while newer evaluations include dynamic, long-horizon, and multi-agent settings. A central challenge is maintaining accurate, query-relevant evidence over time: models still struggle with spatial and temporal reasoning, and stronger memory or exploration must be balanced against inference and navigation costs.