RoboQuest: frontier multimodal agents solve only 23% of embodied exploration tasks
Researchers introduced RoboQuest, a benchmark for goal-directed embodied exploration with ten mobile manipulation tasks built around three kinds of uncertainty: search, manipulation-based inspection, and interactive testing. Five frontier multimodal agents were evaluated through a common visuomotor interface alongside a π0.5 policy fine-tuned on released full-episode demonstrations; the best agent succeeded in only 23% of episodes, and the fine-tuned policy almost never succeeded. Failure analysis attributes only a minority of failures to execution, finding instead that agents often stop exploring too early, decide before observing the required evidence, and rarely prevent or repair disturbances caused by their own exploration.
By isolating the need to actively acquire missing information, the benchmark suggests current multimodal agents' weakness in unfamiliar environments lies more in exploration decisions than in executing the actions themselves.