mlsanityData to 14 Oct 2026

R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO

arXiv 2505.16673 ↗First posted 22 May 2025cs.CV cs.AI cs.CLcited by 52

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

In this work, we aim to incentivize the reasoning ability of Multimodal Large Language Models (MLLMs) via reinforcement learning (RL) and develop an effective approach that mitigates the sparse reward and advantage vanishing issues during RL. To this end, we propose Share-GRPO, a novel RL approach that tackle these issues by exploring and sharing diverse reasoning trajectories over expanded question space. Specifically, Share-GRPO first expands the question space for a given question via data transformation techniques, and then encourages MLLM to effectively explore diverse reasoning trajectories over the expanded question space and shares the discovered reasoning trajectories across the expanded questions during RL. In addition, Share-GRPO also shares reward information during advantage computation, which estimates solution advantages hierarchically across and within question variants, allowing more accurate estimation of relative advantages and improving the stability of policy training. Extensive evaluations over six widely-used reasoning benchmarks showcase the superior performance of our method. Code will be available at https://github.com/HJYao00/R1-ShareVL.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 39 of its 64 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

39 of 64 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning23 Apr
  2. 2025SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models10 Apr
  3. 2025VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning10 Apr
  4. 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement10 Apr
  5. 2025Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought8 Apr
  6. 2025Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models26 Mar
  7. 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles21 Mar
  8. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization13 Mar
  9. 2025MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning10 Mar
  10. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models9 Mar
  11. 2024Improve Vision Language Model Chain-of-thought Reasoning21 Oct
  12. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct
1 more
  1. 2023Multimodal Chain-of-Thought Reasoning in Language Models2 Feb

Other references · 26

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2023Qwen Technical Reportcited by 3,344
  9. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  10. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  11. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  12. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
14 more
  1. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  2. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?cited by 914
  3. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 872
  4. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  5. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 301
  6. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruningcited by 279
  7. 2024Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Searchcited by 175
  8. 2024RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthinesscited by 131
  9. 2025Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learningcited by 69
  10. 2024Sharing Knowledge in Multi-Task Deep Reinforcement Learningcited by 44
  11. 2025GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Imagescited by 39
  12. 2025X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domainscited by 31
  13. 2025Valley2: Exploring Multimodal Models with Scalable Vision-Language Designcited by 21
  14. 2025InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compressioncited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 23; 2026: 29.

52 papers.

Sort:

By area:

  1. 2025Perception-Aware Policy Optimization for Multimodal Reasoningcited by 99
  2. 2025Look-Back: Implicit Visual Re-focusing in MLLM Reasoningcited by 55
  3. 2025Spotlight on Token Perception for Multimodal Reinforcement Learningcited by 39
  4. 2025LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Modelcited by 35
  5. 2025VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoningcited by 26
  6. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  7. 2026MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baselinecited by 20
  8. 2025Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shufflecited by 19
  9. 2025Perception Before Reasoning: Two-Stage Reinforcement Learning for Visual Reasoning in Vision-Language Modelscited by 17
  10. 2025VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Taskscited by 14
  11. 2025MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGIcited by 14
  12. 2025How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMscited by 12
38 more
  1. 2025MAPO: Mixed Advantage Policy Optimizationcited by 11
  2. 2025SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Modelscited by 10
  3. 2025Reinforcement Learning for Large Model: A Surveycited by 9
  4. 2025Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimizationcited by 9
  5. 2026Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoningcited by 9
  6. 2026From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoningcited by 8
  7. 2025What MLLMs Learn about When they Learn about Multimodal Reasoningcited by 6
  8. 2026Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognitioncited by 6
  9. 2026EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Modelscited by 5
  10. 2026Co-Evolving Policy Distillationcited by 5
  11. 2026PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshapingcited by 5
  12. 2025VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Groundingcited by 4
  13. 2025Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generationcited by 4
  14. 2026What does RL improve for Visual Reasoning? A Frankenstein-Style Analysiscited by 4
  15. 2026On Test-Time Scaling for Vision-Language Modelscited by 4
  16. 2025Towards Efficient Multimodal Unified Reasoning Model via Model Mergingcited by 3
  17. 2026DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantagecited by 3
  18. 2026STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answeringcited by 3
  19. 2025Multimodal Policy Internalization for Conversational Agentscited by 2
  20. 2025Strengthening LLMs for Tabular Prediction with Structural Priorscited by 2
  21. 2026Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Modelscited by 2
  22. 2026Reinforcing Multimodal Reasoning Against Visual Degradationcited by 2
  23. 2026Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoningcited by 2
  24. 2026Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spotscited by 2
  25. 2025OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessmentcited by 1
  26. 2025More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language Modelscited by 1
  27. 2026Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Chartscited by 1
  28. 2026LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppressioncited by 1
  29. 2026Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understandingcited by 0
  30. 2026R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?cited by 0
  31. 2026MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learningcited by 0
  32. 2026Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learningcited by 0
  33. 2026Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoningcited by 0
  34. 2026ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Rewardcited by 0
  35. 2026Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoningcited by 0
  36. 2026Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learningcited by 0
  37. 2026SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learningcited by 0
  38. 2026Multi-Branch Policy Optimization for Multimodal Large Language Modelscited by 0

50 most cited of 52 All 52 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
  2. 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
  3. 2026Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models
  4. 2026GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings
  5. 2025Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
  6. 2025Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
  7. 2025Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
  8. 2025Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning