AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

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

Mingrui Wu, Lu Wang, Pu Zhao, Fangkai Yang, Jianjin Zhang, Jianfeng Liu, Yuefeng Zhan, Weihao Han, Hao Sun, Jiayi Ji, Xiaoshuai Sun, Qingwei Lin and 4 more

ICLR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add reasoning trace to RL reprompting (ablation)RePrompt · GenEval overall, FLUXoverall accuracy: 0.68 -> 0.72Improved
add RL on top of SFT (ablation)RePrompt · GenEval overall, FLUXoverall accuracy: 0.69 -> 0.76Improved
add SFT on top of RL (ablation)RePrompt · GenEval overall, FLUXoverall accuracy: 0.72 -> 0.76Improved
use SFT only versus Qwen2.5 3B prompt (ablation)RePrompt · GenEval overall, FLUXoverall accuracy: 0.68 -> 0.69No clear effect
use ensemble ImageReward + VLM reward instead of ImageReward only (ablation)RePrompt · GenEval overall, FLUXoverall accuracy: 0.70 -> 0.72Improved
use ensemble reward instead of VLM reward only (ablation)RePrompt · GenEval overall, FLUXoverall accuracy: 0.69 -> 0.72Improved
apply RePrompt to FLUX promptsFLUX · GenEval positionposition accuracy: 0.18 -> 0.62Improved
apply RePrompt to SD3 prompts (trained with FLUX)SD3 · T2I-CompBench colorcolor score: 0.7941 -> 0.7866Hurt
apply RePrompt to FLUXFLUX · GenEval single objectaccuracy: 0.99 -> 0.98No clear effect
apply RePrompt to FLUXFLUX · T2I-CompBench spatialspatial score: 0.2494 -> 0.3301Improved
RePrompt vs Idea2Img optimizationFLUX · GenEval subset latencylatency: 140 -> 30 s/imgImproved

Later papers that compared with this method

2 later accepted papers report RePrompt as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy