SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

ArXi:2603.28730v1 Announce Type: cross Vision-language models (VLMs) have shown impressive capabilities across diverse tasks, motivating efforts to leverage these models to supervise robot learning. However, when used as evaluators in reinforcement learning (RL), today's strongest models often fail under partial observability and distribution shift, enabling policies to exploit perceptual errors rather than solve the task. To address this limitation, we