Improve model card for Qwen-32B-CyberSearcher with paper, code, description, and metadata

README.md

@@ -1,30 +1,63 @@
 ---
 library_name: transformers
+pipeline_tag: text-generation
+license: mit
 tags:
 - generated_from_trainer
+- deep-search
+- retrieval-augmented-generation
+- web-agent
+- qwen
 model-index:
 - name: Qwen-32B-CyberSearcher
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Qwen-32B-CyberSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
 
-# Qwen-32B-CyberSearcher
+This model is a 32B parameter variant part of the **SimpleDeepSearcher** framework, presented in the paper [SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis](https://huggingface.co/papers/2505.16834).
 
-This model was trained from scratch on an unknown dataset.
+Code: [https://github.com/RUCAIBox/SimpleDeepSearcher](https://github.com/RUCAIBox/SimpleDeepSearcher)
+
+<p align="center">
+  <img src="https://github.com/RUCAIBox/SimpleDeepSearcher/raw/main/assets/simplelog.jpg" alt="SimpleDeepSearcher Logo" width="550"/>
+</p>
 
 ## Model description
 
-More information needed
+SimpleDeepSearcher is a lightweight yet effective framework for enhancing Large Language Models (LLMs) in complex deep search scenarios that require multi-step reasoning and iterative information retrieval. It addresses critical limitations of existing Retrieval-Augmented Generation (RAG) systems by strategically synthesizing high-quality training data from realistic user interactions in live web search environments, coupled with a multi-criteria curation strategy. This approach enables efficient supervised fine-tuning (SFT) with only a small amount of curated data, establishing SFT as a viable pathway for building efficient deep search systems with reduced computational cost and development complexity.
+
+### Key Contributions
+
+-   A real web-based data synthesis framework that simulates realistic user search behaviors, generating multi-turn reasoning and search trajectories.
+-   A multi-criteria data curation strategy that jointly optimizes both input question selection and output response filtering through orthogonal filtering dimensions.
+-   Experimental results demonstrate that SFT on only 871 curated samples enables SimpleDeepSearcher to outperform strong baselines (especially RL-based baselines) on both in-domain and out-of-domain benchmarks.
+
+## Framework Overview
+
+SimpleDeepSearcher achieves intelligent search through efficient supervised fine-tuning (SFT) using minimal, high-quality training data constructed via a systematic data synthesis and curation pipeline.
+
+<p align="center">
+  <img src="https://github.com/RUCAIBox/SimpleDeepSearcher/raw/main/assets/pipeline.png" alt="SimpleDeepSearcher Pipeline" width="800"/>
+</p>
+
+## Overall Performance
+
+SimpleDeepSearcher consistently outperforms all baselines across five benchmark datasets, including both in-domain (2Wiki, MuSiQue) and out-of-domain (Bamboogle, FRAMES, GAIA) settings, demonstrating strong generalization and high data efficiency.
+
+<p align="center">
+  <img src="https://github.com/RUCAIBox/SimpleDeepSearcher/raw/main/assets/overall_performance.png" alt="Overall Performance" width="800"/>
+</p>
 
 ## Intended uses & limitations
 
-More information needed
+This model is intended for advanced deep search scenarios where large language models need to perform multi-step reasoning and iterative information retrieval through web searches. It can be utilized as a core component for building efficient and effective deep search systems.
+
+Limitations may include dependency on the quality of synthesized training data and the performance of the underlying web search API.
 
 ## Training and evaluation data
 
-More information needed
+The model was fine-tuned via Supervised Fine-tuning (SFT) on only 871 curated samples. This high-quality training data was synthesized by simulating realistic user interactions in live web search environments, followed by a multi-criteria curation strategy that optimized the diversity and quality of input and output.
 
 ## Training procedure
 
@@ -45,3 +78,24 @@ The following hyperparameters were used during training:
 - Pytorch 2.5.1+cu124
 - Datasets 2.19.0
 - Tokenizers 0.20.3
+
+## Citation
+
+Please kindly cite our report if they are helpful for your research:
+
+```bibtex
+@article{sun2025simpledeepsearcher,
+  title={SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis},
+  author={Sun, Shuang and Song, Huatong and Wang, Yuhao and Ren, Ruiyang and Jiang, Jinhao and Zhang, Junjie and Bai, Fei and Deng, Jia and Zhao, Wayne Xin and Liu, Zheng and others},
+  journal={arXiv preprint arXiv:2505.16834},
+  year={2025}
+}
+```
+
+## License
+
+This project is released under the [MIT License](https://github.com/RUCAIBox/SimpleDeepSearcher/blob/main/LICENSE).
+
+## Contact
+
+For any questions or feedback, please reach out to us at [sunshuanguns@gmail.com](mailto:sunshuanguns@gmail.com) or [songhuatong123@ruc.edu.cn](mailto:songhuatong123@ruc.edu.cn).