JarvisEvo

JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization

[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent Yunlong Lin, Zixu Lin and Kunjie Lin, etc.

📮 News

• [2026.02.21] 🎉 JarvisEvo has been accepted by CVPR 2026!
• [2025.12.29] We are grateful for the coverage by 机器之心 (link) and 量子位 (link). Thank you for the support!
• [2025.12.16] JarvisEvo's project page, paper are now available!

📦 Model Weights and Datasets

Resource	Type	Size	Download Link	Description
JarvisEvo-8B	Model Weights	~17GB	🤗 Hugging Face	Main model checkpoint for JarvisEvo
ArtEdit-Bench	Dataset	~1GB	🤗 Hugging Face	Evaluation benchmark dataset

Quick Download Commands:

# Download model weights
huggingface-cli download JarvisEvo/JarvisEvo --local-dir ./checkpoints/pretrained/JarvisEvo

# Download datasets
huggingface-cli download JarvisEvo/ArtEdit-Bench --repo-type dataset --local-dir ./datasets/ArtEdit-Bench

🎪 Open-source Plan

• Create repo and project page
• Release Inference code and checkpoints
• Release Agent-to-Lightroom Protocol (server-client communication protocol for multi-machine, multi-GPU training with distributed Lightroom instances)
• Release ArtEdit-Bench
• Release SFT training code
• Release SEPO, RFT training code

🧭 Table of Contents

• 📮 News
• 🎪 Open-source Plan
• 🧭 Overview
  • 📝 Key Features
  • 📊 Visual Comparison
• 💻 Getting Started
  • Batch Inference
  • Training Guide
  • Evaluation
  • Agent-to-Lightroom Protocol
• 🙏 Acknowledgements
• 🌤️ Discussion Group
• 📧 Contact
• 📚 Citation
• 📜 License

🧭 Overview

📝 Key Features

🧠 Interleaved Multimodal Chain-of-Thought (iMCoT)

Closed-Loop Reasoning: "Thinks" with both text and images, validating steps against visual feedback to minimize hallucinations and error propagation.

🔄 Synergistic Editor-Evaluator Optimization (SEPO)

Self-Evolving Framework: A dual-loop reinforcement learning system where the model acts as both editor and evaluator, refining strategies via intrinsic rewards without relying on static external models.

🎨 Unified Preservative & Generative Editing

Comprehensive Toolset: Seamlessly integrates Adobe Lightroom (200+ tools) for precise adjustments and Qwen-Image-Edit for creative synthesis (object removal, style transfer), handling the full spectrum of editing tasks.

🪞 Self-Reflective Learning Mechanism

Autonomous Improvement: Automatically generates reflection trajectories upon suboptimal results, enabling the model to learn from mistakes and continuously optimize its tool selection logic.

📊 Visual Comparison

💻 Getting Started

For batch inference, please follow:

• Batch Inference

For training, please follow:

• Training Guide

For evaluation, please follow:

• Evaluation

For Agent-to-Lightroom Protocol Detail, please follow:

• Agent-to-Lightroom Protocol

🙏 Acknowledgements

We would like to express our gratitude to LLaMA-Factory for their valuable open-source contributions which have provided important technical references for our work.

🌤️ Discussion Group

If you have any questions during the trial, running or deployment, feel free to join our WeChat group discussion!

📧 Contact

For any questions or inquiries, please reach out to us:

• Yunlong Lin: [email protected]

---

📚 Citation

If you find JarvisEvo useful in your research, please consider citing:

@article{lin2025jarvisevo,
  title={JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization},
  author={Lin, Yunlong and Wang, Linqing and Lin, Kunjie and Lin, Zixu and Gong, Kaixiong and Li, Wenbo and Lin, Bin and Li, Zhenxi and Zhang, Shiyi and Peng, Yuyang and others},
  journal={arXiv preprint arXiv:2511.23002},
  year={2025}
}

---

📜 License

The JarvisEvo model weights, inference code, and associated materials are made freely available by Yunlong Lin for academic research, personal study, and other non-commercial uses under the JarvisEvo Non-Commercial License.

By downloading, accessing, or using the JarvisEvo model, you agree to the terms of this license. Please refer to the JarvisEvo Non-Commercial License v1.0 file in this repository for the full terms and conditions.

Commercial Use: If you wish to use the JarvisEvo model or its derivatives for commercial purposes, please contact me at [[email protected]] to request a commercial license.