# RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning

arXiv: https://arxiv.org/abs/2505.17540 · HTML: https://mlsanity.com/paper/2505.17540/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 42 of its 63 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 30 of 42)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization](https://mlsanity.com/paper/2503.10615/) (2025)
- [R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2503.12937/) (2025)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning](https://mlsanity.com/paper/2503.21620/) (2025)
- [T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://mlsanity.com/paper/2505.00703/) (2025)
- [SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer](https://mlsanity.com/paper/2501.18427/) (2025)
- [Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step](https://mlsanity.com/paper/2501.13926/) (2025)
- [Perception-R1: Pioneering Perception Policy with Reinforcement Learning](https://mlsanity.com/paper/2504.07954/) (2025)
- [Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models](https://mlsanity.com/paper/2409.10695/) (2024)
- [Improving Text-to-Image Consistency via Automatic Prompt Optimization](https://mlsanity.com/paper/2403.17804/) (2024)
- [SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL](https://mlsanity.com/paper/2504.11455/) (2025)
- [A Dense Reward View on Aligning Text-to-Image Diffusion with Preference](https://mlsanity.com/paper/2402.08265/) (2024)
- [IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation](https://mlsanity.com/paper/2410.07171/) (2024)
- [Boosting MLLM Reasoning with Text-Debiased Hint-GRPO](https://mlsanity.com/paper/2503.23905/) (2025)
- [A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning](https://mlsanity.com/paper/2503.00897/) (2025)

## Built on by (most cited first, 24 of 24)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting](https://mlsanity.com/paper/2509.04545/) (2025)
- [Flow caching for autoregressive video generation](https://mlsanity.com/paper/2602.10825/) (2026)
- [GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning](https://mlsanity.com/paper/2601.18543/) (2026)
- [RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling](https://mlsanity.com/paper/2510.20206/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning](https://mlsanity.com/paper/2509.22761/) (2025)
- [Agentic Retoucher for Text-To-Image Generation](https://mlsanity.com/paper/2601.02046/) (2026)
- [Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models](https://mlsanity.com/paper/2512.15347/) (2025)
- [M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning](https://mlsanity.com/paper/2602.06166/) (2026)
- [MICON-Bench: Benchmarking and Enhancing Multi-Image Context Image Generation in Unified Multimodal Models](https://mlsanity.com/paper/2602.19497/) (2026)
- [SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models](https://mlsanity.com/paper/2604.12617/) (2026)
- [A Systematic Post-Train Framework for Video Generation](https://mlsanity.com/paper/2604.25427/) (2026)
- [POET: Preference Optimization for Enhanced Text-to-Image Generation](https://mlsanity.com/paper/2510.12041/) (2025)
- [MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing](https://mlsanity.com/paper/2601.04589/) (2026)
- [BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation](https://mlsanity.com/paper/2603.02816/) (2026)
- [EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis](https://mlsanity.com/paper/2603.20828/) (2026)
- [PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment](https://mlsanity.com/paper/2510.00430/) (2025)
- [Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation](https://mlsanity.com/paper/2606.08492/) (2026)
- [Panoptic Scene Program Diffusion Transformer](https://mlsanity.com/paper/2609.31780/) (2026)
- [EvoGen-Harness: Learning Where and How to Evolve Image-Generation Harnesses](https://mlsanity.com/paper/2610.00383/) (2026)
- [SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation](https://mlsanity.com/paper/2610.22264/) (2026)

## Abstract (arXiv)

Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language models (LLMs), these methods frequently generate stylistic or unrealistic content due to insufficient grounding in visual semantics and real-world composition. Inspired by recent advances in reasoning for language model, we propose RePrompt, a novel reprompting framework that introduces explicit reasoning into the prompt enhancement process via reinforcement learning. Instead of relying on handcrafted rules or stylistic rewrites, our method trains a language model to generate structured, self-reflective prompts by optimizing for image-level outcomes. The tailored reward models assesse the generated images in terms of human preference, semantic alignment, and visual composition, providing indirect supervision to refine prompt generation. Our approach enables end-to-end training without human-annotated data. Experiments on GenEval and T2I-Compbench show that RePrompt significantly boosts spatial layout fidelity and compositional generalization across diverse T2I backbones, establishing new state-of-the-art results.