EviBack: Reinforcement Learning Search Agents via Evidence-Constrained Teacher Backoff

Xiao Ma^*  Zhiquan Hu^*  Yi Wei  Chenchen Zhao  Yijun Chen  Jicheng Zhao  Yuming Li^i†  Chuang Dai

NextAI Research Institute, Chery Group.

^*Equal Contribution, ^i†Corresponding Author

📣 Updates

• [2026.07.28] 🔥 Our paper is in public on arxiv.

Quick Start

Environment Setup

🛠️Installation for Linux

1. Create a conda environment

2. Other dependencies

pip install -r requirements.txt

🧱Model Preparation

Models	Download Link	Notes
	🤗 Huggingface	Base model
	🤗 Huggingface
	🤗 Huggingface

-- The weights of EviBack is organized as follows.

./flash/
├── 
├── 
└── diffusion_pytorch_model.safetensors

📒 Citation

If you find our work useful for your research, please consider citing the paper :

@article{ma2026eviback,
title={Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff},
  author={Xiao Ma, Zhiquan Hu, Yi Wei, Chenchen Zhao, Yijun Chen, Jicheng Zhao, Yuming Li, Chuang Dai},
  year={2026},
  eprint={2607.23955},
  archivePrefix={arXiv},
  primaryClass={cs.AI}
}

📜 License

The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations.