# ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning

arXiv: https://arxiv.org/abs/2605.07477 · HTML: https://mlsanity.com/paper/2605.07477/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 23 of its 70 references that are in the map.
- First posted on arXiv 8 May 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 23 of 23)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation](https://mlsanity.com/paper/2404.02733/) (2024)
- [Ovis2.5 Technical Report](https://mlsanity.com/paper/2508.11737/) (2025)
- [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://mlsanity.com/paper/2505.14460/) (2025)
- [EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing](https://mlsanity.com/paper/2509.26346/) (2025)
- [DreamOmni2: Multimodal Instruction-based Editing and Generation](https://mlsanity.com/paper/2510.06679/) (2025)
- [UniREditBench: A Unified Reasoning-based Image Editing Benchmark](https://mlsanity.com/paper/2511.01295/) (2025)
- [LMM4Edit: Benchmarking and Evaluating Multimodal Image Editing with LMMs](https://mlsanity.com/paper/2507.16193/) (2025)
- [Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization](https://mlsanity.com/paper/2509.21871/) (2025)
- [EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing](https://mlsanity.com/paper/2603.14916/) (2026)
- [Graph Neural Network Approach to Semantic Type Detection in Tables](https://mlsanity.com/paper/2405.00123/) (2024)
- [CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions](https://mlsanity.com/paper/2603.26174/) (2026)

## Built on by (most cited first, 1 of 1)

- [Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation](https://mlsanity.com/paper/2610.01670/) (2026)

## Abstract (arXiv)

Recent text-guided image editing (TIE) models have achieved remarkable progress, however, many edited results still suffer from artifacts, unintended modifications, and suboptimal aesthetics. Although several benchmarks and evaluation methods have been proposed, most existing approaches rely on scalar scores and lack interpretability. This limitation largely stems from the absence of high-quality interpretation datasets for TIE and effective reward models to train interpretable evaluators. To address these challenges, we introduce ReasonEdit-22K, the first dataset that combines 22K edited images with 113K Chain-of-Thought (CoT) samples, along with 1.3M human judgments assessing these interpretations in terms of logicality, accuracy, and usefulness. Building upon this dataset, we propose RE-Reward, a multimodal large language model (MLLM)-based reward model designed to provide human-aligned feedback for evaluating interpretable reasoning in image editing. Furthermore, we develop ReasonEdit, which is trained using reward signals derived from RE-Reward and the Group Relative Policy Optimization (GRPO) algorithm to learn an interpretable evaluation model. Extensive experiments demonstrate that ReasonEdit achieves superior alignment with human preferences and exhibits strong generalization across public benchmarks. In addition, it is capable of generating high-quality interpretable evaluation text, enabling more transparent and trustworthy assessment for image editing. The code is available at https://github.com/IntMeGroup/ReasonEdit.