Visually-Guided Policy Optimization for Multimodal Reasoning

• URL: http://arxiv.org/abs/2604.09349v1
• Date: Fri, 10 Apr 2026 14:22:38 GMT
• Title: Visually-Guided Policy Optimization for Multimodal Reasoning
• Abstract summary: We propose Visually-Guided Policy Optimization (VGPO) to reinforce visual focus during policy optimization.<n> VGPO initially introduces a Visual Attention Compensation mechanism that leverages visual similarity to localize and amplify visual cues.<n>We show that VGPO achieves better visual activation and superior performance in mathematical multimodal reasoning and visual-dependent tasks.
• Score: 60.035908460318126
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 papers

• Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning [13.390348642117557]
  Long chain-of-thought (CoT) reasoning improves large vision-dependence models, but visual information often fades during generation.<n>Existing methods either re-inject vision inference at or train policies for stronger grounding.<n>We study this problem from an information-theoretic standpoint and derive a lower bound on the downstream visual gain of a one-step intervention.
  arXiv  Detail & Related papers  (2026-05-10T15:53:11Z)
• Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models [65.57985131861399]
  hallucinations are strongly correlated with cognitive bifurcation points that often exhibit high entropy states.<n>We propose V-STAR, a lightweight, holistic training paradigm designed to internalize visually aware reasoning capabilities.
  arXiv  Detail & Related papers  (2026-04-11T13:59:05Z)
• Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models [66.96421290733126]
  Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation.<n>We propose textbfDeepVision-VLA, built on a textbfVision-Language Mixture-of-Transformers (VL-MoT) framework.<n>DeepVision-VLA outperforms prior state-of-the-art methods by 9.0% and 7.5% on simulated and real-world tasks, respectively.
  arXiv  Detail & Related papers  (2026-03-16T17:59:54Z)
• Spotlight on Token Perception for Multimodal Reinforcement Learning [65.97597482517425]
  Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Vision-Language Models (LVLMs)<n>In this paper, we undertake a pioneering exploration of multimodal RLVR through the novel perspective of token perception.<n>We propose Visually-Perceptive Policy Optimization (VPPO), a novel policy gradient algorithm that explicitly leverages token perception to refine the learning signal.
  arXiv  Detail & Related papers  (2025-10-10T11:25:33Z)
• Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning [79.34909830834464]
  Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in complex visual environments.<n>We show that visual complexity strongly correlates with attention entropy, negatively impacting reasoning performance.<n>We propose Contrastive Attention Refinement for Visual Enhancement (CARVE), a training-free method that extracts task-relevant visual signals through attention contrasting at the pixel level.
  arXiv  Detail & Related papers  (2025-09-08T09:20:04Z)
• A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs [3.2228025627337864]
  This paper introduces a structured evaluation framework to dissect the perception-reasoning interface in Vision-Language Models (VLMs)<n>We propose three distinct evaluation paradigms, mirroring human problem-solving strategies.<n>Applying this framework, we demonstrate that CA, leveraging powerful language models for reasoning over rich, independently generated descriptions, achieves new state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2025-01-23T12:42:42Z)
• Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence [69.86946427928511]
  We investigate the internal mechanisms driving hallucination in large vision-language models (LVLMs)<n>We introduce Vision-aware Head Divergence (VHD), a metric that quantifies the sensitivity of attention head outputs to visual context.<n>We propose Vision-aware Head Reinforcement (VHR), a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads.
  arXiv  Detail & Related papers  (2024-12-18T15:29:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.