Add pipeline tag, library metadata and research links

Hi! I'm Niels from the Hugging Face community team. I've opened this PR to improve the model card for Gen-Searcher-8B.

Specifically, I have:
- Added the `library_name: transformers` and `pipeline_tag: image-text-to-text` metadata.
- Specified the `license: apache-2.0`.
- Added links to the paper, the official project page, and the GitHub repository for better discoverability and documentation.
- Included a BibTeX citation section.

These changes will help users discover and use the model more effectively on the Hub.

README.md

@@ -1,29 +1,25 @@
 ---
-datasets:
-- GenSearcher/Train-Data
 base_model:
 - Qwen/Qwen3-VL-8B-Instruct
+datasets:
+- GenSearcher/Train-Data
+library_name: transformers
+pipeline_tag: image-text-to-text
+license: apache-2.0
 ---
 
 # Gen-Searcher-8B Model
 
+This repository contains the Gen-Searcher-8B model presented in [Gen-Searcher: Reinforcing Agentic Search for Image Generation](https://arxiv.org/abs/2603.28767).
 
-This repository contains the Gen-Searcher-8B model presented in: [Gen-Searcher](https://arxiv.org/abs/2603.28767)
-
-For inference, please refer to:
-
-Code: https://github.com/tulerfeng/Gen-Searcher
-
-
-
+[**Project Page**](https://gen-searcher.vercel.app/) | [**GitHub Repository**](https://github.com/tulerfeng/Gen-Searcher) | [**Paper**](https://arxiv.org/abs/2603.28767)
 
 # 👀 Intro
 
 <div align="center">
-  <img src="https://github.com/tulerfeng/Gen-Searcher/blob/main/assets/teaser.jpg?raw=true" alt="Descriptive alt text" width="80%">
+  <img src="https://github.com/tulerfeng/Gen-Searcher/blob/main/assets/teaser.jpg?raw=true" alt="Gen-Searcher Teaser" width="80%">
 </div>
 
-
 We introduce **Gen-Searcher**, as the first attempt to train a multimodal **deep research agent** for image generation that requires complex real-world knowledge. Gen-Searcher can **search the web, browse evidence, reason over multiple sources, and search visual references** before generation, enabling more accurate and up-to-date image synthesis in real-world scenarios.
 
 We build two dedicated training datasets **Gen-Searcher-SFT-10k**, **Gen-Searcher-RL-6k** and one new benchmark **KnowGen** for search-grounded image generation. 
@@ -32,18 +28,29 @@ Gen-Searcher achieves significant improvements, delivering **15+ point gains on
 
 All code, models, data, and benchmark are fully released.
 
-
-
-
 ## 🎥 Demo
 
 #### Inference Process Example
 
 <div align="center">
-  <img src="https://github.com/tulerfeng/Gen-Searcher/blob/main/assets/example.jpg?raw=true" alt="Descriptive alt text" width="85%">
+  <img src="https://github.com/tulerfeng/Gen-Searcher/blob/main/assets/example.jpg?raw=true" alt="Inference Process Example" width="85%">
 </div>
 
-
 For more examples, please refer to our website [[🌐Project Page]](https://gen-searcher.vercel.app/) 
 
+## 🚀 Training and Inference
+
+For detailed instructions on setup, SFT/RL training, and inference, please refer to the [official GitHub repository](https://github.com/tulerfeng/Gen-Searcher).
+
+## 📐 Citation
+
+If you find our work helpful for your research, please consider citing our work:
 
+```bibtex
+@article{feng2025gensearcher,
+  title={Gen-Searcher: Reinforcing Agentic Search for Image Generation},
+  author={Feng, Kaituo and Zhang, Manyuan and Chen, Shuang and Lin, Yunlong and Fan, Kaixuan and Jiang, Yilei and Li, Hongyu and Zheng, Dian and Wang, Chenyang and Yue, Xiangyu},
+  journal={arXiv preprint arXiv:2603.28767},
+  year={2025}
+}
+```