RetouchAgent: Towards Interactive and Explainable Image Retouching with MLLM Agents
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29901-29910
DOI: 10.1609/aaai.v40i35.40237 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shuo Zhang und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Although deep learning-based image retouching has made significant progress, its inherent subjectivity renders current black-box methods limited in interactivity and explainability. Among existing efforts, parameter-controlled methods aim to improve interactivity, but often suffer from ambiguous semantics and lack support for natural language control. Reinforcement learning–based explainability methods are constrained by low-dimensional and limited action spaces, which result in suboptimal performance. To address the above issues, we propose RetouchAgent, a novel framework that leverages collaboration among multiple MLLM agents for image retouching. Our method consists of the following key steps: (1) Retrieval: By constructing a multimodal retouching database, we enable an ICL sample retrieval mechanism guided by retouching intent. (2) Engine: Leveraging the vision-language understanding capabilities of MLLM, a carefully designed prompting strategy, and a dedicated operation library, we enable precise and controllable image retouching. (3) Reflection: We evaluate each retouching interaction and optimize the retouching process for progressive result refinement. Finally, through multiple rounds of collaboration among MLLM agents, RetouchAgent achieves state-of-the-art performance in quantitative and qualitative evaluations.
Zitieren
APA
Zhang, S., & Yang, X. (2026). RetouchAgent: Towards Interactive and Explainable Image Retouching with MLLM Agents. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29901-29910. https://doi.org/10.1609/aaai.v40i35.40237
Vancouver
Zhang S, Yang X. RetouchAgent: Towards Interactive and Explainable Image Retouching with MLLM Agents. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29901-29910. doi:10.1609/aaai.v40i35.40237
BibTeX
@article{Zhang2026,
author = {Zhang, Shuo and Yang, Xinyu},
title = {RetouchAgent: Towards Interactive and Explainable Image Retouching with MLLM Agents},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {35},
pages = {29901--29910},
doi = {10.1609/aaai.v40i35.40237}
}
EUVIMED