mlsanityData to 7 Oct 2026

MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

arXiv 2503.07365 ↗First posted 10 Mar 2025cs.CVcited by 294

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

DeepSeek R1, and o1 have demonstrated powerful reasoning capabilities in the text domain through stable large-scale reinforcement learning. To enable broader applications, some works have attempted to transfer these capabilities to multimodal reasoning. However, these efforts have been limited by the limited difficulty of selected tasks and relatively small training scales, making it challenging to demonstrate strong multimodal reasoning abilities. To address this gap, we introduce the MMK12 dataset and MM-EUREKA with 7B and 32B parameters. The former is a high-quality multimodal mathematics reasoning dataset featuring diverse knowledge domains with human-verified answers and solution processes. The latter is a multimodal model employing rule-based reinforcement learning on MMK12, utilizing online filtering and two-stage training strategy to enhance training stability. MM-EUREKA demonstrates remarkable performance gains in multimodal mathematical reasoning, outperforming previous powerful models like InternVL2.5-78B or InternVL2.5-38B-MPO. In particular, MM-EUREKA achieves competitive or superior performance compared to both open-source and closed-source models, and trails slightly behind o1 in multidisciplinary reasoning tasks. We open-source our complete pipeline to foster further research in this area. We release all our codes, models, data, etc. at https://github.com/ModalMinds/MM-EUREKA

Key facts. Cited by 294 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 19 of its 39 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

19 of 39 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling6 Dec
  2. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale6 Dec
  3. 2024Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization15 Nov
  4. 2024MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine11 Jul
  5. 2024We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?1 Jul
  6. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct

Other references · 13

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2024GPT-4o System Cardcited by 4,467
  6. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  7. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  8. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  9. 2025Process Reinforcement through Implicit Rewardscited by 478
  10. 2024VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Modelscited by 443
  11. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 376
  12. 2024SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuningcited by 345
1 more
  1. 2024Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoningcited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 167; 2026: 127.

294 papers.

Sort:

By area:

  1. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learningcited by 398
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 296
  4. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoningcited by 217
  5. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  6. 2025OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learningcited by 163
  7. 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvementcited by 144
  8. 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cyclescited by 122
  9. 2025Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Searchcited by 116
  10. 2025Perception-Aware Policy Optimization for Multimodal Reasoningcited by 95
  11. 2025Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learningcited by 86
  12. 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agentscited by 73
38 more
  1. 2025Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoningcited by 67
  2. 2025TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoningcited by 59
  3. 2025LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Callingcited by 58
  4. 2025Look-Back: Implicit Visual Re-focusing in MLLM Reasoningcited by 54
  5. 2025R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPOcited by 52
  6. 2025OneThinker: All-in-one Reasoning Model for Image and Videocited by 52
  7. 2025Improved Visual-Spatial Reasoning via R1-Zero-Like Trainingcited by 51
  8. 2025HumanOmniV2: From Understanding to Omni-Modal Reasoning with Contextcited by 50
  9. 2025Understanding Aha Moments: from External Observations to Internal Mechanismscited by 48
  10. 2025Kwai Keye-VL Technical Reportcited by 47
  11. 2025Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learningcited by 46
  12. 2025MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoningcited by 45
  13. 2025Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuningcited by 44
  14. 2025VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learningcited by 41
  15. 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoningcited by 37
  16. 2025MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resourcescited by 37
  17. 2025Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Playcited by 37
  18. 2025Spotlight on Token Perception for Multimodal Reinforcement Learningcited by 37
  19. 2025OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipecited by 37
  20. 2025Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzlescited by 36
  21. 2025Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Modelscited by 35
  22. 2025VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Searchcited by 34
  23. 2025Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoningcited by 34
  24. 2025First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Trainingcited by 34
  25. 2025LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Modelcited by 34
  26. 2025We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoningcited by 32
  27. 2025Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuningcited by 31
  28. 2025X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domainscited by 30
  29. 2025ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RLcited by 30
  30. 2025G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learningcited by 29
  31. 2025One RL to See Them All: Visual Triple Unified Reinforcement Learningcited by 29
  32. 2025Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understandingcited by 28
  33. 2025VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinkingcited by 27
  34. 2025SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learningcited by 27
  35. 2026MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methodscited by 27
  36. 2025EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learningcited by 26
  37. 2025Reinforcing Video Reasoning with Focused Thinkingcited by 26
  38. 2025VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoningcited by 26

50 most cited of 294 All 294 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Multimodal Mathematical Reasoning with Diverse Solving Perspective
  2. 2025MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
  3. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
  4. 2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
  5. 2025LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
  6. 2025Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
  7. 2024Diving into Self-Evolving Training for Multimodal Reasoning
  8. 2025Unlocking Multimodal Mathematical Reasoning via Process Reward Model