ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning
This work provides an incremental improvement for users struggling with complex image editing tasks, particularly those involving nuanced and context-aware edits.
This paper addresses the challenge of complex, multi-step image editing instructions by proposing ImageEdit-R1, a multi-agent framework that uses reinforcement learning to coordinate specialized vision-language and generative agents. The system outperforms individual closed-source diffusion models and other multi-agent frameworks on various image editing datasets.
With the rapid advancement of commercial multi-modal models, image editing has garnered significant attention due to its widespread applicability in daily life. Despite impressive progress, existing image editing systems, particularly closed-source or proprietary models, often struggle with complex, indirect, or multi-step user instructions. These limitations hinder their ability to perform nuanced, context-aware edits that align with human intent. In this work, we propose ImageEdit-R1, a multi-agent framework for intelligent image editing that leverages reinforcement learning to coordinate high-level decision-making across a set of specialized, pretrained vision-language and generative agents. Each agent is responsible for distinct capabilities--such as understanding user intent, identifying regions of interest, selecting appropriate editing actions, and synthesizing visual content--while reinforcement learning governs their collaboration to ensure coherent and goal-directed behavior. Unlike existing approaches that rely on monolithic models or hand-crafted pipelines, our method treats image editing as a sequential decision-making problem, enabling dynamic and context-aware editing strategies. Experimental results demonstrate that ImageEdit-R1 consistently outperforms both individual closed-source diffusion models and alternative multi-agent framework baselines across multiple image editing datasets.