
RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments
RobotWorld introduces a cross-embodiment robot-use benchmark spanning 84 tasks and evaluates whether multimodal agents can convert perception and computation into verifier-confirmed physical execution.
Zhiqin Yang, Chenxin Li, Xiaomeng Hu · 49 views · Oct 7, 2026
Robot BenchmarkEmbodied AI
Oct 7, 2026