Paper
PhotoAgent: Agentic Photo Editing with Exploratory Visual Aesthetic Planning
Authors
Mingde Yao, Zhiyuan You, Tam-King Man, Menglu Wang, Tianfan Xue
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://github.com/mdyao/PhotoAgent.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.22809v1</id>\n <title>PhotoAgent: Agentic Photo Editing with Exploratory Visual Aesthetic Planning</title>\n <updated>2026-02-26T09:46:06Z</updated>\n <link href='https://arxiv.org/abs/2602.22809v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.22809v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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://github.com/mdyao/PhotoAgent.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-02-26T09:46:06Z</published>\n <arxiv:comment>A fully automated, intelligent photo-editing agent that autonomously plans multi-step aesthetic enhancements, smartly chooses diverse editing tools, and enables everyday users to achieve professional-looking results without crafting complex prompts. Project page: https://github.com/mdyao/PhotoAgent</arxiv:comment>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Mingde Yao</name>\n </author>\n <author>\n <name>Zhiyuan You</name>\n </author>\n <author>\n <name>Tam-King Man</name>\n </author>\n <author>\n <name>Menglu Wang</name>\n </author>\n <author>\n <name>Tianfan Xue</name>\n </author>\n </entry>"
}