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

🌍 Introduction

ArtEdit-Bench. We construct ArtEdit-Bench, comprising two subsets: (1) ArtEdit-Bench-Lr (800 samples: 400 English, 400 Chinese), selected from the ArtEdit-Lr dataset. It evaluates both global and local fine-grained retouching capabilities. (2) ArtEdit-Bench-Eval (200 English samples), sampled from ArtEdit-Eval, is used to fairly assess the model’s self-evaluation capabilities against assessment models.

📜 Citation

If you find our paper and code useful in your research, please consider giving a star ⭐ and citation 📝.

@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}
}