# Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information

arXiv: https://arxiv.org/abs/2505.23558 · HTML: https://mlsanity.com/paper/2505.23558/

## Key facts

- Cited by 28 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 53 references that are in the map.
- First posted on arXiv 29 May 2025.

## 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)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [Analyzing and Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2310.00754/) (2023)
- [We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?](https://mlsanity.com/paper/2407.01284/) (2024)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [Step-level Value Preference Optimization for Mathematical Reasoning](https://mlsanity.com/paper/2406.10858/) (2024)
- [The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering](https://mlsanity.com/paper/2502.03628/) (2025)
- [Effectively Controlling Reasoning Models through Thinking Intervention](https://mlsanity.com/paper/2503.24370/) (2025)
- [SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark](https://mlsanity.com/paper/2402.05138/) (2024)
- [Introducing Visual Perception Token into Multimodal Large Language Model](https://mlsanity.com/paper/2502.17425/) (2025)
- [Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark](https://mlsanity.com/paper/2410.14702/) (2024)
- [LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception](https://mlsanity.com/paper/2504.15362/) (2025)
- [Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains](https://mlsanity.com/paper/2501.14431/) (2025)

## Built on by (most cited first, 28 of 28)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis](https://mlsanity.com/paper/2509.23652/) (2025)
- [Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings](https://mlsanity.com/paper/2602.13823/) (2026)
- [Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Models](https://mlsanity.com/paper/2509.13031/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models](https://mlsanity.com/paper/2510.21978/) (2025)
- [Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance](https://mlsanity.com/paper/2602.01047/) (2026)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis](https://mlsanity.com/paper/2602.12395/) (2026)
- [CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation](https://mlsanity.com/paper/2604.10410/) (2026)
- [PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning](https://mlsanity.com/paper/2605.13467/) (2026)
- [DF-LLaVA: Unlocking MLLMs for Synthetic Image Detection via Knowledge Injection and Conflict-Driven Self-Reflection](https://mlsanity.com/paper/2509.14957/) (2025)
- [Visual Access Boundaries in Vision-Language Model Reasoning](https://mlsanity.com/paper/2607.12815/) (2026)
- [VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models](https://mlsanity.com/paper/2603.00207/) (2026)
- [VIDA: A Dataset for Visually Dependent Ambiguity in Multimodal Machine Translation](https://mlsanity.com/paper/2605.02035/) (2026)
- [Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization](https://mlsanity.com/paper/2605.11974/) (2026)
- [Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning](https://mlsanity.com/paper/2605.28160/) (2026)
- [DeepLatent: Think with Images via Parallel Latent Visual Reasoning](https://mlsanity.com/paper/2606.00562/) (2026)
- [ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-Examination](https://mlsanity.com/paper/2608.04385/) (2026)
- [SGG-Rrm 3: From Next-Token Prediction to End-to-End Unbiased Scene Graph Generation](https://mlsanity.com/paper/2603.07961/) (2026)
- [Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning](https://mlsanity.com/paper/2605.09614/) (2026)
- [Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models](https://mlsanity.com/paper/2605.18160/) (2026)
- [CogniRoute: Learning to Route Social Evidence in Omni-Modal Models](https://mlsanity.com/paper/2606.20970/) (2026)
- [FOCUS: Decoupling Expert Personas in LLMs to Enhance Domain Expert Capabilities](https://mlsanity.com/paper/2608.05611/) (2026)
- [Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue](https://mlsanity.com/paper/2608.24521/) (2026)
- [Certified Interface Aliases: Exact Collisions in Vision-Language Preprocessing, and When They Exist](https://mlsanity.com/paper/2609.33003/) (2026)
- [ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory](https://mlsanity.com/paper/2610.05097/) (2026)

## Abstract (arXiv)

Inference time scaling drives extended reasoning to enhance the performance of Vision-Language Models (VLMs), thus forming powerful Vision-Language Reasoning Models (VLRMs). However, long reasoning dilutes visual tokens, causing visual information to receive less attention and may trigger hallucinations. Although introducing text-only reflection processes shows promise in language models, we demonstrate that it is insufficient to suppress hallucinations in VLMs. To address this issue, we introduce Qwen-LookAgain (Qwen-LA), a novel VLRM designed to mitigate hallucinations by incorporating a vision-text reflection process that guides the model to re-attention visual information during reasoning. We first propose a reinforcement learning method Balanced Reflective Policy Optimization (BRPO), which guides the model to decide when to generate vision-text reflection on its own and balance the number and length of reflections. Then, we formally prove that VLRMs lose attention to visual tokens as reasoning progresses, and demonstrate that supplementing visual information during reflection enhances visual attention. Therefore, during training and inference, Visual Token COPY and Visual Token ROUTE are introduced to force the model to re-attention visual information at the visual level, addressing the limitations of text-only reflection. Experiments on multiple visual QA datasets and hallucination metrics indicate that Qwen-LA achieves leading accuracy performance while reducing hallucinations. Our code is available at: https://github.com/Liar406/Look_Again