# Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs

arXiv: https://arxiv.org/abs/2603.25077 · HTML: https://mlsanity.com/paper/2603.25077/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 26 Mar 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, 24 of 24)

- [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)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?](https://mlsanity.com/paper/2407.01284/) (2024)
- [Reasoning with Exploration: An Entropy Perspective](https://mlsanity.com/paper/2506.14758/) (2025)
- [Thyme: Think Beyond Images](https://mlsanity.com/paper/2508.11630/) (2025)
- [Perception-Aware Policy Optimization for Multimodal Reasoning](https://mlsanity.com/paper/2507.06448/) (2025)
- [RLPR: Extrapolating RLVR to General Domains without Verifiers](https://mlsanity.com/paper/2506.18254/) (2025)
- [Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought](https://mlsanity.com/paper/2504.05599/) (2025)
- [R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning](https://mlsanity.com/paper/2505.02835/) (2025)
- [Visual Agentic Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.14246/) (2025)
- [Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning](https://mlsanity.com/paper/2504.16656/) (2025)
- [Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward](https://mlsanity.com/paper/2506.07218/) (2025)
- [Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start](https://mlsanity.com/paper/2505.22334/) (2025)
- [Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation](https://mlsanity.com/paper/2506.09736/) (2025)
- [AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization](https://mlsanity.com/paper/2504.15619/) (2025)
- [Rethinking Visual Content Refinement in Low-Shot CLIP Adaptation](https://mlsanity.com/paper/2407.14117/) (2024)
- [Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization](https://mlsanity.com/paper/2602.21743/) (2026)

## Built on by (most cited first, 9 of 9)

- [Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR](https://mlsanity.com/paper/2605.20164/) (2026)
- [Structured Role-Aware Policy Optimization for Multimodal Reasoning](https://mlsanity.com/paper/2605.07274/) (2026)
- [Experience Augmented Policy Optimization for LLM Reasoning](https://mlsanity.com/paper/2606.30420/) (2026)
- [Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR](https://mlsanity.com/paper/2603.26126/) (2026)
- [Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs](https://mlsanity.com/paper/2608.03450/) (2026)
- [Video-FLAIR: Not Whether to Reason, But How](https://mlsanity.com/paper/2608.26495/) (2026)
- [Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning](https://mlsanity.com/paper/2609.18057/) (2026)
- [Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoning](https://mlsanity.com/paper/2609.35228/) (2026)
- [Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning](https://mlsanity.com/paper/2609.36572/) (2026)

## Abstract (arXiv)

Extending Reinforcement Learning with Verifiable Rewards (RLVR) to multimodal large language models (MLLMs) faces a fundamental challenge: their responses inherently interleave perception-related tokens, which ground visual content, with reasoning-related tokens, which construct reasoning chains. These token types instantiate distinct yet interdependent capacities -- visual grounding and symbolic reasoning -- making isolated optimization insufficient. Through token-level empirical analysis, we demonstrate that optimizing either perception- or reasoning-only tokens consistently underperforms full optimization, underscoring their inherent coupling. To address this, we propose a plug-and-play Token-Reweighting (ToR) strategy that explicitly models this interdependence by identifying critical tokens of both types and dynamically reweighting them during RLVR training. Applied on top of existing methods (e.g., GRPO and DAPO), ToR delivers consistent performance gains across multiple multi-modal reasoning benchmarks, achieving state-of-the-art performance with both accurate visual grounding and coherent reasoning.