mlsanityData to 14 Oct 2026

GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning

arXiv 2505.17022 ↗First posted 22 May 2025cs.CV cs.AI cs.CLcited by 52

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of such prompts requires explicit reasoning about the semantic content and spatial layout. We present GoT-R1, a framework that applies reinforcement learning to enhance semantic-spatial reasoning in visual generation. Building upon the Generation Chain-of-Thought approach, GoT-R1 enables models to autonomously discover effective reasoning strategies beyond predefined templates through carefully designed reinforcement learning. To achieve this, we propose a dual-stage multi-dimensional reward framework that leverages MLLMs to evaluate both the reasoning process and final output, enabling effective supervision across the entire generation pipeline. The reward system assesses semantic alignment, spatial accuracy, and visual quality in a unified approach. Experimental results demonstrate significant improvements on T2I-CompBench benchmark, particularly in compositional tasks involving precise spatial relationships and attribute binding. GoT-R1 advances the state-of-the-art in image generation by successfully transferring sophisticated reasoning capabilities to the visual generation domain. To facilitate future research, we make our code and pretrained models publicly available at https://github.com/gogoduan/GoT-R1.

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 31 of its 56 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

31 of 56 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT1 May
  2. 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles21 Mar
  3. 2025GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing13 Mar
  4. 2025R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization13 Mar
  5. 2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement9 Mar

Other references · 26

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2025Qwen2.5-VL Technical Reportcited by 5,587
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  8. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  9. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  10. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  11. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  12. 2024Emu3: Next-Token Prediction is All You Needcited by 781
14 more
  1. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  2. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
  3. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 340
  4. 2024SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generationcited by 331
  5. 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 304
  6. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 301
  7. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 163
  8. 2024Randomized Autoregressive Visual Generationcited by 127
  9. 2024Loong: Generating Minute-level Long Videos with Autoregressive Language Modelscited by 99
  10. 2025Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learningcited by 69
  11. 2024Parallelized Autoregressive Visual Generationcited by 60
  12. 2025Bridging Continuous and Discrete Tokens for Autoregressive Visual Generationcited by 29
  13. 2024PUMA: Empowering Unified MLLM with Multi-granular Visual Generationcited by 20
  14. 2023InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generationcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 26; 2026: 26.

52 papers.

Sort:

By area:

  1. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  2. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 199
  3. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  4. 2025T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generationcited by 38
  5. 2025FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmarkcited by 38
  6. 2025MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoningcited by 35
  7. 2025Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?cited by 34
  8. 2025JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimizationcited by 31
  9. 2026GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoningcited by 24
  10. 2026Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddingscited by 24
  11. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  12. 2025CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Imagescited by 23
38 more
  1. 2025SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Modelscited by 22
  2. 2025Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Taskscited by 22
  3. 2025Object Detection with Multimodal Large Vision-Language Models: An In-depth Reviewcited by 14
  4. 2026Demystifying Video Reasoningcited by 14
  5. 2025VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoningcited by 12
  6. 2025Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMscited by 10
  7. 2025SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Modelscited by 10
  8. 2025Reinforcement Learning for Large Model: A Surveycited by 9
  9. 2025MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generationcited by 9
  10. 2025PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewardscited by 9
  11. 2026Understanding Reward Hacking in Text-to-Image Reinforcement Learningcited by 9
  12. 2025MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoningcited by 8
  13. 2025Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editingcited by 6
  14. 2026Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Modelscited by 6
  15. 2025Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generationcited by 5
  16. 2026Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Modelscited by 5
  17. 2025From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generationcited by 4
  18. 2026Wan-R1: Verifiable-Reinforcement Learning for Video Reasoningcited by 4
  19. 2026Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Modelscited by 4
  20. 2026MiLDEdit: Reasoning-Based Multi-Layer Design Document Editingcited by 3
  21. 2026Generative Visual Chain-of-Thought for Image Editingcited by 3
  22. 2026FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generationcited by 3
  23. 2026Meta-CoT: Enhancing Granularity and Generalization in Image Editingcited by 3
  24. 2025Efficient Medical VIE via Reinforcement Learningcited by 2
  25. 2025Image-POSER: Reflective RL for Multi-Expert Image Generation and Editingcited by 2
  26. 2026Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Rewardcited by 2
  27. 2026IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generationcited by 2
  28. 2025OSPO: Object-Centric Self-Improving Preference Optimization for Text-to-Image Generationcited by 1
  29. 2026MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generationcited by 1
  30. 2026B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentationcited by 1
  31. 2026ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoningcited by 0
  32. 2026From "What" to "How": Constrained Reasoning for Autoregressive Image Generationcited by 0
  33. 2026Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Inductioncited by 0
  34. 2026UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generationcited by 0
  35. 2026CogniRoute: Learning to Route Social Evidence in Omni-Modal Modelscited by 0
  36. 2026WithEveryone: Unified Planning and Identity Grounding for Group Image Generationcited by 0
  37. 2026LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residualscited by 0
  38. 2026The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generationcited by 0

50 most cited of 52 All 52 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
  2. 2025Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
  3. 2026UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
  4. 2025ThinkGen: Generalized Thinking for Visual Generation
  5. 2025Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback
  6. 2026RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection
  7. 2025Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation
  8. 2025Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances