mlsanityData to 7 Oct 2026

MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models

arXiv 2409.00147 ↗First posted 30 Aug 2024cs.CL cs.AIcited by 69

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

The rapid development of large language models (LLMs) has spurred extensive research into their domain-specific capabilities, particularly mathematical reasoning. However, most open-source LLMs focus solely on mathematical reasoning, neglecting the integration with visual injection, despite the fact that many mathematical tasks rely on visual inputs such as geometric diagrams, charts, and function plots. To fill this gap, we introduce MultiMath-7B, a multimodal large language model that bridges the gap between math and vision. MultiMath-7B is trained through a four-stage process, focusing on vision-language alignment, visual and math instruction-tuning, and process-supervised reinforcement learning. We also construct a novel, diverse and comprehensive multimodal mathematical dataset, MultiMath-300K, which spans K-12 levels with image captions and step-wise solutions. MultiMath-7B achieves state-of-the-art (SOTA) performance among open-source models on existing multimodal mathematical benchmarks and also excels on text-only mathematical benchmarks. Our model and dataset are available at textcolorblueurlhttps://github.com/pengshuai-rin/MultiMath.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 39 references that are in the map. First posted on arXiv 30 Aug 2024.

Builds on

21 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models25 Jun

Other references · 20

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  7. 2023Mistral 7Bcited by 3,065
  8. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  9. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  10. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  11. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  12. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
8 more
  1. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 701
  2. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  3. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  4. 2023Llemma: An Open Language Model For Mathematicscited by 385
  5. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 376
  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. 2023CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?cited by 89

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 46; 2026: 19.

69 papers.

Sort:

By area:

  1. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 653
  2. 2025Unlocking Multimodal Mathematical Reasoning via Process Reward Modelcited by 64
  3. 2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learningcited by 51
  4. 2025MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoningcited by 45
  5. 2025SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Rewardcited by 45
  6. 2025MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoningcited by 45
  7. 2025Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Rewardcited by 45
  8. 2025Advancing Multimodal Reasoning via Reinforcement Learning with Cold Startcited by 41
  9. 2024ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detectioncited by 37
  10. 2025MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resourcescited by 37
  11. 2025VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selectioncited by 34
  12. 2025First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Trainingcited by 34
38 more
  1. 2024Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoningcited by 32
  2. 2025MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contextscited by 32
  3. 2025We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoningcited by 32
  4. 2025Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoningcited by 30
  5. 2025MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervisioncited by 28
  6. 2025VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoningcited by 26
  7. 2024BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devicescited by 25
  8. 2025AStar: Boosting Multimodal Reasoning with Automated Structured Thinkingcited by 25
  9. 2025Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMscited by 16
  10. 2025Math Blind: Failures in Diagram Understanding Undermine Reasoning in MLLMscited by 15
  11. 2025VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Modelscited by 14
  12. 2025Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbationcited by 14
  13. 2025MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Modelscited by 13
  14. 2024Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptionscited by 12
  15. 2025Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMscited by 12
  16. 2025MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problemscited by 10
  17. 2025Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directionscited by 10
  18. 2025Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNetscited by 10
  19. 2025Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approachcited by 8
  20. 2025Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoningcited by 8
  21. 2025Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoningcited by 7
  22. 2026Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understandingcited by 6
  23. 2025Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMscited by 5
  24. 2026CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solvingcited by 5
  25. 2026DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoningcited by 5
  26. 2025Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughputcited by 4
  27. 2025CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoningcited by 4
  28. 2025Multimodal Mathematical Reasoning with Diverse Solving Perspectivecited by 4
  29. 2025CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understandingcited by 4
  30. 2025Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learningcited by 4
  31. 2026Logics-Parsing-Omni Technical Reportcited by 4
  32. 2025The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insightscited by 3
  33. 2025Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understandingcited by 3
  34. 2025Enhancing Scientific Visual Question Answering via Vision-Caption aware Supervised Fine-Tuningcited by 3
  35. 2025InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoningcited by 2
  36. 2025MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuningcited by 2
  37. 2026NoReGeo: Non-Reasoning Geometry Benchmarkcited by 2
  38. 2026GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervisioncited by 2

50 most cited of 69 All 69 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency
  2. 2026M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models
  3. 2024Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark
  4. 2025SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning
  5. 2024InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
  6. 2025Integrating Visual Interpretation and Linguistic Reasoning for Math Problem Solving
  7. 2026Func-R1: Incentivizing Mathematical Function Reasoning in Multimodal Large Language Models
  8. 2025Forgotten Polygons: Multimodal Large Language Models are Shape-Blind