RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward

TL;DR

RetouchIQ introduces a reinforcement learning framework using a generalist reward model to enable large language model agents to perform instruction-based, high-quality, and explainable image retouching, advancing professional editing tools.

Contribution

The paper presents RetouchIQ, a novel RL-based approach with a generalist reward model for instruction-driven image editing, surpassing traditional rule-based methods.

Findings

Significant improvement in semantic consistency of edited images.

Enhanced perceptual quality over previous systems.

Established a new benchmark with a 190k instruction-reasoning dataset.

Abstract

Recent advances in multimodal large language models (MLLMs) have shown great potential for extending vision-language reasoning to professional tool-based image editing, enabling intuitive and creative editing. A promising direction is to use reinforcement learning (RL) to enable MLLMs to reason about and execute optimal tool-use plans within professional image-editing software. However, training remains challenging due to the lack of reliable, verifiable reward signals that can reflect the inherently subjective nature of creative editing. In this work, we introduce RetouchIQ, a framework that performs instruction-based executable image editing through MLLM agents guided by a generalist reward model. RetouchIQ interprets user-specified editing intentions and generates corresponding, executable image adjustments, bridging high-level aesthetic goals with precise parameter control. To move beyond conventional, rule-based rewards that compute similarity against a fixed reference image using handcrafted metrics, we propose a generalist reward model, an RL fine-tuned MLLM that evaluates edited results through a set of generated metrics on a case-by-case basis. Then, the reward model provides scalar feedback through multimodal reasoning, enabling reinforcement learning with high-quality, instruction-consistent gradients. We curate an extended dataset with 190k instruction-reasoning pairs and establish a new benchmark for instruction-based image editing. Experiments show that RetouchIQ substantially improves both semantic consistency and perceptual quality over previous MLLM-based and diffusion-based editing systems. Our findings demonstrate the potential of generalist reward-driven MLLM agents as flexible, explainable, and executable assistants for professional image editing.