# VLM-R3: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought

arXiv: https://arxiv.org/abs/2505.16192 · HTML: https://mlsanity.com/paper/2505.16192/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 65 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization](https://mlsanity.com/paper/2501.03262/) (2025)
- [MathPrompter: Mathematical Reasoning using Large Language Models](https://mlsanity.com/paper/2303.05398/) (2023)
- [Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers](https://mlsanity.com/paper/2408.06195/) (2024)
- [Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation](https://mlsanity.com/paper/2307.15337/) (2023)
- [A Survey of Reasoning with Foundation Models](https://mlsanity.com/paper/2312.11562/) (2023)
- [Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings](https://mlsanity.com/paper/2305.02317/) (2023)
- [AStar: Boosting Multimodal Reasoning with Automated Structured Thinking](https://mlsanity.com/paper/2502.02339/) (2025)
- [Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning](https://mlsanity.com/paper/2410.03321/) (2024)
- [Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems](https://mlsanity.com/paper/2210.05075/) (2022)

## Built on by (most cited first, 30 of 49)

- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [DeepEyesV2: Toward Agentic Multimodal Model](https://mlsanity.com/paper/2511.05271/) (2025)
- [Latent Visual Reasoning](https://mlsanity.com/paper/2509.24251/) (2025)
- [Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception](https://mlsanity.com/paper/2602.11858/) (2026)
- [From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2509.25373/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images](https://mlsanity.com/paper/2510.11718/) (2025)
- [LensWalk: Agentic Video Understanding by Planning How You See in Videos](https://mlsanity.com/paper/2603.24558/) (2026)
- [Think Twice to See More: Iterative Visual Reasoning in Medical VLMs](https://mlsanity.com/paper/2510.10052/) (2025)
- [Imagination Helps Visual Reasoning, But Not Yet in Latent Space](https://mlsanity.com/paper/2602.22766/) (2026)
- [DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model](https://mlsanity.com/paper/2508.13238/) (2025)
- [OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving](https://mlsanity.com/paper/2512.14044/) (2025)
- [Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought](https://mlsanity.com/paper/2603.22847/) (2026)
- [RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding](https://mlsanity.com/paper/2510.27261/) (2025)
- [What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning](https://mlsanity.com/paper/2602.08346/) (2026)
- [Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning](https://mlsanity.com/paper/2601.02918/) (2026)
- [VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language Models](https://mlsanity.com/paper/2511.18823/) (2025)
- [PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models](https://mlsanity.com/paper/2512.01843/) (2025)
- [HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning](https://mlsanity.com/paper/2603.17024/) (2026)
- [CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating](https://mlsanity.com/paper/2605.11723/) (2026)
- [CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding](https://mlsanity.com/paper/2508.00378/) (2025)
- [Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding](https://mlsanity.com/paper/2602.14225/) (2026)
- [TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding](https://mlsanity.com/paper/2606.08464/) (2026)
- [Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning](https://mlsanity.com/paper/2602.11909/) (2026)
- [See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection](https://mlsanity.com/paper/2604.24339/) (2026)
- [Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model](https://mlsanity.com/paper/2605.12163/) (2026)
- [VistaHop: Benchmarking Long-Horizon Visual DeepSearch](https://mlsanity.com/paper/2606.03273/) (2026)
- [DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation](https://mlsanity.com/paper/2607.02220/) (2026)
- [VIRTUE: Visual-Interactive Text-Image Universal Embedder](https://mlsanity.com/paper/2510.00523/) (2025)
- [Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios](https://mlsanity.com/paper/2604.14041/) (2026)

## Abstract (arXiv)

Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on and revisiting of visual regions to achieve precise grounding of textual reasoning in visual evidence. We introduce VLM-R3 (Visual Language Model with Region Recognition and Reasoning), a framework that equips an MLLM with the ability to (i) decide when additional visual evidence is needed, (ii) determine where to ground within the image, and (iii) seamlessly weave the relevant sub-image content back into an interleaved chain-of-thought. The core of our method is Region-Conditioned Reinforcement Policy Optimization (R-GRPO), a training paradigm that rewards the model for selecting informative regions, formulating appropriate transformations (e.g. crop, zoom), and integrating the resulting visual context into subsequent reasoning steps. To bootstrap this policy, we compile a modest but carefully curated Visuo-Lingual Interleaved Rationale (VLIR) corpus that provides step-level supervision on region selection and textual justification. Extensive experiments on MathVista, ScienceQA, and other benchmarks show that VLM-R3 sets a new state of the art in zero-shot and few-shot settings, with the largest gains appearing on questions demanding subtle spatial reasoning or fine-grained visual cue extraction.