AI RESEARCH
MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
arXiv CS.CL
•
ArXi:2605.01520v1 Announce Type: cross Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising solution by optimizing policies using answer correctness signals. Despite their effectiveness, prevailing RLVR methods face two critical limitations. First, much of the sampling budget is wasted on trajectories doomed to fail due to early visual description errors.