PhotoAgent: Agentic Photo Editing with Exploratory Visual Aesthetic Planning

TL;DR

PhotoAgent is an autonomous photo editing system that plans and executes multi-step aesthetic edits using visual feedback, reducing user effort and improving image quality.

Contribution

It introduces a decision-making framework for autonomous image editing with aesthetic planning and a new benchmark for evaluation.

Findings

PhotoAgent outperforms baseline methods in instruction adherence.

It achieves higher visual quality in edited images.

The system effectively plans multi-step edits using visual feedback.

Abstract

With the recent fast development of generative models, instruction-based image editing has shown great potential in generating high-quality images. However, the quality of editing highly depends on carefully designed instructions, placing the burden of task decomposition and sequencing entirely on the user. To achieve autonomous image editing, we present PhotoAgent, a system that advances image editing through explicit aesthetic planning. Specifically, PhotoAgent formulates autonomous image editing as a long-horizon decision-making problem. It reasons over user aesthetic intent, plans multi-step editing actions via tree search, and iteratively refines results through closed-loop execution with memory and visual feedback, without requiring step-by-step user prompts. To support reliable evaluation in real-world scenarios, we introduce UGC-Edit, an aesthetic evaluation benchmark consisting of 7,000 photos and a learned aesthetic reward model. We also construct a test set containing 1,017 photos to systematically assess autonomous photo editing performance. Extensive experiments demonstrate that PhotoAgent consistently improves both instruction adherence and visual quality compared with baseline methods. The project page is https://mdyao.github.io/PhotoAgent/.