LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models
LIBERO-Recover is a benchmark testing how robotic models recover from failures during manipulation tasks, moving beyond simple success metrics. It collects real execution failures and creates 1,000+ scenarios across four difficulty levels—from simple action retries to complex environmental reasoning. The research shows that while models succeed in ideal tests, they often fail when faced with real-world errors.