AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

RetouchAgent: Towards Interactive and Explainable Image Retouching with MLLM Agents

Shuo Zhang, Xinyu Yang

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Reinforcement learning for visual reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes RetouchAgent, an MLLM-agent framework for interactive, explainable image retouching driven by natural language instructions.

Problem

Deep learning image retouching is subjective and black-box, so existing methods lack interactivity and explainability; parameter-controlled methods have ambiguous semantics and no natural-language control.

Approach

Uses multimodal LLM agents to interpret natural-language retouching requests and explain the edits, aiming to combine interactivity with explainability beyond parameter-controlled and RL-based approaches.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add text-intent retrieval (lambda_text 0.4) to image-only retrieval (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 23.50 -> 26.02Improved
increase text weight beyond 0.4 to 0.8 (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 26.02 -> 25.48Hurt
use 3 ICL examples instead of fewer or more (ablation)RetouchAgent · MIT-Adobe FiveK (5 experts avg, 480p)PSNRImproved
add system prompt constraints and examples (ablation)RetouchAgent · MIT-Adobe FiveK (full dataset)success rate: 26.8% -> 99.4%Improved
use the designed operation library instead of GMIC (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 20.21 -> 26.02Improved
use the designed operation library instead of OpenCV (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 21.65 -> 26.02Improved
add curve operations to the operation library (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 23.12 -> 26.02Improved
add target image analysis to CoT (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 24.32 -> 26.02Improved
add expert example analysis to CoT (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 24.16 -> 26.02Improved
add difference analysis to CoT (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 23.82 -> 26.02Improved
add reflection agent (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 21.35 -> 26.02Improved
use full reflection history instead of only previous round (ablation)RetouchAgent · MIT-Adobe FiveK Expert C (480p)PSNR: 24.76 -> 26.02Improved

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