Update arXiv link

README.md

@@ -97,12 +97,9 @@ We further analyze the model’s test-time scaling behavior. S1-DeepResearch sho
 👉 **[https://github.com/ScienceOne-AI/S1-DeepResearch](https://github.com/ScienceOne-AI/S1-DeepResearch)**
 
 
-
 ---
 
 
----
-
 ## 📜 协议与引用 | License & Citation
 
 ### License
@@ -115,11 +112,14 @@ This model is licensed under **Apache License 2.0**.
 
 
 ```bibtex
-@software{s1agent2025,
-    title={S1-DeepResearch: High-Performance Deep Research Agent},
-    author={ScienceOne Team},
-    year={2025},
-    url={https://github.com/ScienceOne-AI/S1-DeepResearch},
+@misc{2026s1deepresearch,
+      title={S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents}, 
+      author={Yao Dong and Xinglin Xiao and Liwei Dong and Xinlong Jin and Zhengbo Li and Heng Zhang and Duyun Wang and Nan Xu},
+      year={2026},
+      eprint={2606.15367},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2606.15367}, 
 }
 ```
 
@@ -135,13 +135,4 @@ This model is licensed under **Apache License 2.0**.
 
 本模型为研究预览版本,可能存在局限性。在生产环境使用前请充分测试。模型输出结果仅供参考,不构成专业建议。
 
-**This model is a research preview and may have limitations. Please test thoroughly before production use. Model outputs are for reference only and do not constitute professional advice.**
-
----
-
-<div align="center">
-
-**Made with ❤️ by ScienceOne Team**
-
-</div>
-
+**This model is a research preview and may have limitations. Please test thoroughly before production use. Model outputs are for reference only and do not constitute professional advice.**