← back
arXivYining Hong, Jiageng Liu, Han Yin, Manling Li, Leonidas Guibas, Li Fei-Fei, Jiajun Wu, Yejin ChoiMon, May 18, 2026, 10:59 AM PDT
score 12.9
2cites

Benchmark tests whether AI agents actively explore to understand 3D space

Original: ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop

Source: arxiv.org

Writing ELI5 summary…