# Visually-Guided Policy Optimization for Multimodal Reasoning

arXiv: https://arxiv.org/abs/2604.09349 · HTML: https://mlsanity.com/paper/2604.09349/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 65 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 29 of 29)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning](https://mlsanity.com/paper/2503.07365/) (2025)
- [LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts](https://mlsanity.com/paper/2407.04973/) (2024)
- [GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning](https://mlsanity.com/paper/2504.02546/) (2025)
- [Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens](https://mlsanity.com/paper/2506.17218/) (2025)
- [Latent Visual Reasoning](https://mlsanity.com/paper/2509.24251/) (2025)
- [Perception-Aware Policy Optimization for Multimodal Reasoning](https://mlsanity.com/paper/2507.06448/) (2025)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [Tree Search for LLM Agent Reinforcement Learning](https://mlsanity.com/paper/2509.21240/) (2025)
- [Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs](https://mlsanity.com/paper/2510.17771/) (2025)
- [VisPlay: Self-Evolving Vision-Language Models from Images](https://mlsanity.com/paper/2511.15661/) (2025)
- [Spotlight on Token Perception for Multimodal Reinforcement Learning](https://mlsanity.com/paper/2510.09285/) (2025)
- [More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models](https://mlsanity.com/paper/2509.25848/) (2025)
- [Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning](https://mlsanity.com/paper/2511.18437/) (2025)
- [Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation](https://mlsanity.com/paper/2601.20614/) (2026)
- [On the Faithfulness of Visual Thinking: Measurement and Enhancement](https://mlsanity.com/paper/2510.23482/) (2025)
- [Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration](https://mlsanity.com/paper/2602.11241/) (2026)
- [SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning](https://mlsanity.com/paper/2510.16416/) (2025)

## Built on by (most cited first, 11 of 11)

- [Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs](https://mlsanity.com/paper/2606.26387/) (2026)
- [Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR](https://mlsanity.com/paper/2605.30912/) (2026)
- [Escape the Language Prior: Mitigating Late-Stage Modality Collapse in Audio Reasoning via Modality-Aware Policy Optimization](https://mlsanity.com/paper/2605.27741/) (2026)
- [Structured Role-Aware Policy Optimization for Multimodal Reasoning](https://mlsanity.com/paper/2605.07274/) (2026)
- [Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution](https://mlsanity.com/paper/2605.08887/) (2026)
- [RISE: Reliable Improvement in Self-Evolving Vision-Language Models](https://mlsanity.com/paper/2605.20914/) (2026)
- [VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct](https://mlsanity.com/paper/2606.23543/) (2026)
- [SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning](https://mlsanity.com/paper/2607.13931/) (2026)
- [Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry](https://mlsanity.com/paper/2608.30457/) (2026)
- [Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning](https://mlsanity.com/paper/2609.18057/) (2026)
- [Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning](https://mlsanity.com/paper/2610.04918/) (2026)

## Abstract (arXiv)

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. The code has been released at https://github.com/wzb-bupt/VGPO.