AI RESEARCH

Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought

arXiv CS.CV

ArXi:2603.22847v1 Announce Type: new Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable Rewards (RLVR) methods typically optimize reasoning at a coarse granularity, treating CoT uniformly without distinguishing their varying degrees of visual grounding.