mlsanityData to 7 Oct 2026

MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification

arXiv 2502.13383 ↗First posted 19 Feb 2025cs.CL cs.CV cs.LGcited by 39

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is still a lack of a strong MM-Verifier. In this paper, we introduce MM-Verifier and MM-Reasoner to enhance multimodal reasoning through longer inference and more robust verification. First, we propose a two-step MM verification data synthesis method, which combines a simulation-based tree search with verification and uses rejection sampling to generate high-quality Chain-of-Thought (COT) data. This data is then used to fine-tune the verification model, MM-Verifier. Additionally, we present a more efficient method for synthesizing MMCOT data, bridging the gap between text-based and multimodal reasoning. The synthesized data is used to fine-tune MM-Reasoner. Our MM-Verifier outperforms all larger models on the MathCheck, MathVista, and MathVerse benchmarks. Moreover, MM-Reasoner demonstrates strong effectiveness and scalability, with performance improving as data size increases. Finally, our approach achieves strong performance when combining MM-Reasoner and MM-Verifier, reaching an accuracy of 65.3 on MathVista, surpassing GPT-4o (63.8) with 12 rollouts.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 37 of its 60 references that are in the map. First posted on arXiv 19 Feb 2025.

Builds on

37 of 60 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs10 Jan
  2. 2025Unlocking Multimodal Mathematical Reasoning via Process Reward Model8 Jan
  3. 2025Virgo: A Preliminary Exploration on Reproducing o1-like MLLM3 Jan
  4. 2024Diving into Self-Evolving Training for Multimodal Reasoning23 Dec
  5. 2024Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning27 Nov
  6. 2024Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning16 Aug
  7. 2024MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine11 Jul
  8. 2024Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models25 Jun
  9. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct

Other references · 28

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2023Qwen Technical Reportcited by 3,273
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  7. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  8. 2023A Survey of Large Language Modelscited by 2,537
  9. 2024A Survey on LLM-as-a-Judgecited by 1,384
  10. 2025s1: Simple test-time scalingcited by 1,311
  11. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 718
  12. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
16 more
  1. 2025LIMO: Less is More for Reasoningcited by 488
  2. 2025Process Reinforcement through Implicit Rewardscited by 478
  3. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 465
  4. 2025The Lessons of Developing Process Reward Models in Mathematical Reasoningcited by 402
  5. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  6. 2023SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Modelscited by 283
  7. 2023G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Modelcited by 208
  8. 2023Multimodal Large Language Models: A Surveycited by 193
  9. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 162
  10. 2024Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8Bcited by 156
  11. 2024A Survey of Multimodal Large Language Model from A Data-centric Perspectivecited by 73
  12. 2024Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklistcited by 48
  13. 2023SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-trainingcited by 41
  14. 2024EAGLE: Elevating Geometric Reasoning through LLM-empowered Visual Instruction Tuningcited by 16
  15. 2024BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Searchcited by 13
  16. 2024Hologram Reasoning for Solving Algebra Problems with Geometry Diagramscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 24; 2026: 15.

39 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  3. 2025Zebra-CoT: A Dataset for Interleaved Vision Language Reasoningcited by 78
  4. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Modelscited by 29
  5. 2025Heimdall: test-time scaling on the generative verificationcited by 26
  6. 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Modelscited by 22
  7. 2025MARS: toward more efficient multi-agent collaboration for LLM reasoningcited by 13
  8. 2025Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verificationcited by 12
  9. 2025Sherlock: Self-Correcting Reasoning in Vision-Language Modelscited by 11
  10. 2025DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoningcited by 10
  11. 2025Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmarkcited by 10
  12. 2025OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Drivingcited by 9
27 more
  1. 2025Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoningcited by 7
  2. 2025Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Modelscited by 7
  3. 2025Faithful-First Reasoning, Planning, and Acting for Multimodal LLMscited by 7
  4. 2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimizationcited by 5
  5. 2026Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimizationcited by 5
  6. 2026AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAGcited by 5
  7. 2026PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignmentcited by 5
  8. 2025A Survey of Deep Learning for Geometry Problem Solvingcited by 4
  9. 2025RecTok: Reconstruction Distillation along Rectified Flowcited by 4
  10. 2026Towards Next-Generation LLM Training: From the Data-Centric Perspectivecited by 3
  11. 2026OpenWorldLib: A Unified Codebase and Definition of Advanced World Modelscited by 3
  12. 2026Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agentscited by 3
  13. 2025PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Modelscited by 2
  14. 2025Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Frameworkcited by 2
  15. 2025From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Modelscited by 1
  16. 2025Generative Giants, Retrieval Weaklings: Why do Multimodal Large Language Models Fail at Multimodal Retrieval?cited by 1
  17. 2026TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videoscited by 1
  18. 2026Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQAcited by 1
  19. 2026Granularity-Regulated Adaptive Computational Efficiency for Optimal Verification in Test-Time Scalingcited by 1
  20. 2025GeoRef: Referring Expressions in Geometry via Task Formulation, Synthetic Supervision, and Reinforced MLLM-based Solutionscited by 0
  21. 2025Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancingcited by 0
  22. 2026Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervisioncited by 0
  23. 2026SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safetycited by 0
  24. 2026A Nash Equilibrium Framework For Training-Free Multimodal Step Verificationcited by 0
  25. 2026VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensuscited by 0
  26. 2026Physics as the label for measuring and correcting materials reasoning in multimodal modelscited by 0
  27. 2026Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025TIM-PRM: Verifying multimodal reasoning with Tool-Integrated PRM
  2. 2024Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
  3. 2025MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
  4. 2025MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
  5. 2025Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
  6. 2024General Purpose Verification for Chain of Thought Prompting
  7. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
  8. 2023GraphReason: Enhancing Reasoning Capabilities of Large Language Models through A Graph-Based Verification Approach