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

Qiucheng Wu, Jing Shi, Simon Jenni, Kushal Kafle, Tianyu Wang, Shiyu Chang, Handong Zhao

CVPR · 2026

Research summary

An MLLM-based agent framework for instruction-driven image retouching with a generalist reward model.

Uses multimodal large language model agents with generalist reward to perform instruction-based image retouching without task-specific training.