# Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO

arXiv: https://arxiv.org/abs/2505.17017 · HTML: https://mlsanity.com/paper/2505.17017/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 32 of its 67 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2410.13848/) (2024)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study](https://mlsanity.com/paper/2404.10719/) (2024)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://mlsanity.com/paper/2505.00703/) (2025)
- [Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step](https://mlsanity.com/paper/2501.13926/) (2025)
- [MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine](https://mlsanity.com/paper/2407.08739/) (2024)
- [Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs](https://mlsanity.com/paper/2402.14740/) (2024)
- [CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models](https://mlsanity.com/paper/2503.22342/) (2025)

## Built on by (most cited first, 30 of 31)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE](https://mlsanity.com/paper/2507.21802/) (2025)
- [Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation](https://mlsanity.com/paper/2508.09987/) (2025)
- [Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning](https://mlsanity.com/paper/2508.20751/) (2025)
- [TIIF-Bench: How Does Your T2I Model Follow Your Instructions?](https://mlsanity.com/paper/2506.02161/) (2025)
- [MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.05331/) (2025)
- [Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark](https://mlsanity.com/paper/2510.26802/) (2025)
- [UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation](https://mlsanity.com/paper/2510.18701/) (2025)
- [GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning](https://mlsanity.com/paper/2601.18543/) (2026)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation](https://mlsanity.com/paper/2511.16671/) (2025)
- [Generative Universal Verifier as Multimodal Meta-Reasoner](https://mlsanity.com/paper/2510.13804/) (2025)
- [NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation](https://mlsanity.com/paper/2601.02204/) (2026)
- [MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition](https://mlsanity.com/paper/2512.07348/) (2025)
- [Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation](https://mlsanity.com/paper/2512.10949/) (2025)
- [MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning](https://mlsanity.com/paper/2509.22761/) (2025)
- [From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation](https://mlsanity.com/paper/2604.02355/) (2026)
- [Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editing](https://mlsanity.com/paper/2510.08157/) (2025)
- [ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning](https://mlsanity.com/paper/2602.03425/) (2026)
- [CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation](https://mlsanity.com/paper/2603.08652/) (2026)
- [EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2602.23802/) (2026)
- [POET: Preference Optimization for Enhanced Text-to-Image Generation](https://mlsanity.com/paper/2510.12041/) (2025)
- [VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation](https://mlsanity.com/paper/2604.02467/) (2026)
- [VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation](https://mlsanity.com/paper/2601.02256/) (2026)
- [Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling](https://mlsanity.com/paper/2510.16751/) (2025)
- [Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning](https://mlsanity.com/paper/2601.04672/) (2026)
- [HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation](https://mlsanity.com/paper/2604.09629/) (2026)
- [Optimizing Visual Generative Models via Distribution-wise Rewards](https://mlsanity.com/paper/2607.02291/) (2026)
- [Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning](https://mlsanity.com/paper/2605.10445/) (2026)
- [MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning](https://mlsanity.com/paper/2606.17888/) (2026)

## Abstract (arXiv)

Recent advancements underscore the significant role of Reinforcement Learning (RL) in enhancing the Chain-of-Thought (CoT) reasoning capabilities of large language models (LLMs). Two prominent RL algorithms, Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO), are central to these developments, showcasing different pros and cons. Autoregressive image generation, also interpretable as a sequential CoT reasoning process, presents unique challenges distinct from LLM-based CoT reasoning. These encompass ensuring text-image consistency, improving image aesthetic quality, and designing sophisticated reward models, rather than relying on simpler rule-based rewards. While recent efforts have extended RL to this domain, these explorations typically lack an in-depth analysis of the domain-specific challenges and the characteristics of different RL strategies. To bridge this gap, we provide the first comprehensive investigation of the GRPO and DPO algorithms in autoregressive image generation, evaluating their in-domain performance and out-of-domain generalization, while scrutinizing the impact of different reward models on their respective capabilities. Our findings reveal that GRPO and DPO exhibit distinct advantages, and crucially, that reward models possessing stronger intrinsic generalization capabilities potentially enhance the generalization potential of the applied RL algorithms. Furthermore, we systematically explore three prevalent scaling strategies to enhance both their in-domain and out-of-domain proficiency, deriving unique insights into efficiently scaling performance for each paradigm. We hope our study paves a new path for inspiring future work on developing more effective RL algorithms to achieve robust CoT reasoning in the realm of autoregressive image generation. Code is released at https://github.com/ZiyuGuo99/Image-Generation-CoT