Visually-Guided Policy Optimization for Multimodal Reasoning

arXiv:2604.09349v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly advanced the reasoning ability of vision-language models (VLMs). However, the inherent text-dominated nature of VLMs often leads to insufficient visual faithfulness, characterized by sparse attention activation to visual tokens. More importantly, our empirical analysis reveals that temporal visual forgetting along reasoning steps exacerbates this deficiency. To bridge this gap, we propose Visually-Guided Policy Optimization (VGPO), a novel framework to reinforce visual focus during policy optimization. Specifically, VGPO initially introduces a Visual Attention Compensation mechanism that leverages visual similarity to localize and amplify visual cues, while progressively elevating visual expectations in later steps to counteract visual forgetting. Building on this mechanism, we implement a dual-grained advantage re-weighting strategy: the intra-trajectory level highlights tokens exhibiting relatively high visual activation, while the inter-trajectory level prioritizes trajectories demonstrating superior visual accumulation. Extensive experiments demonstrate that VGPO achieves better visual activation and superior performance in mathematical multimodal reasoning and visual-dependent tasks.

Related

• Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
• Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models
• OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
• SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
• SSPO: Subsentence-level Policy Optimization

Source: arXiv cs.AI | 2026-04-13