AI RESEARCH
Perception-Aware Policy Optimization for Multimodal Reasoning
arXiv CS.CL
•
ArXi:2507.06448v5 Announce Type: replace Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with robust multi-step reasoning abilities. However, its design and optimizations remain tailored to purely textual domains, resulting in suboptimal performance when applied to multimodal reasoning tasks. In particular, we observe that a major source of error in current multimodal reasoning lies in the perception of visual inputs.