Improve: Add Tool-Star citation to model card (#2)

- Improve: Add Tool-Star citation to model card (8a903f22cfe4f77d3b75c3e0faa137728f0e725b)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,18 +1,18 @@
 ---
-license: mit
-pipeline_tag: text-generation
-library_name: transformers
-datasets:
-- dongguanting/ARPO-SFT-54K
-- dongguanting/ARPO-RL-Reasoning-10K
-- dongguanting/ARPO-RL-DeepSearch-1K
-language: en
 base_model:
 - Qwen/Qwen2.5-3B-Instruct
 - Qwen/Qwen2.5-7B-Instruct
 - meta-llama/Llama-3.1-8B-Instruct
 - Qwen/Qwen3-8B-Instruct
 - Qwen/Qwen3-14B-Instruct
+datasets:
+- dongguanting/ARPO-SFT-54K
+- dongguanting/ARPO-RL-Reasoning-10K
+- dongguanting/ARPO-RL-DeepSearch-1K
+language: en
+library_name: transformers
+license: mit
+pipeline_tag: text-generation
 ---
 
 # Agentic Reinforced Policy Optimization (ARPO)
@@ -114,6 +114,30 @@ If you find this work helpful, please cite our paper:
       primaryClass={cs.LG},
       url={https://arxiv.org/abs/2507.19849}, 
 }
+@article{dong2025toolstar,
+  author       = {Guanting Dong and
+                  Yifei Chen and
+                  Xiaoxi Li and
+                  Jiajie Jin and
+                  Hongjin Qian and
+                  Yutao Zhu and
+                  Hangyu Mao and
+                  Guorui Zhou and
+                  Zhicheng Dou and
+                  Ji{-}Rong Wen},
+  title        = {Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement
+                  Learning},
+  journal      = {CoRR},
+  volume       = {abs/2505.16410},
+  year         = {2025},
+  url          = {https://doi.org/10.48550/arXiv.2505.16410},
+  doi          = {10.48550/ARXIV.2505.16410},
+  eprinttype    = {arXiv},
+  eprint       = {2505.16410},
+  timestamp    = {Thu, 26 Jun 2025 07:49:34 +0200},
+  biburl       = {https://dblp.org/rec/journals/corr/abs-2505-16410.bib},
+  bibsource    = {dblp computer science bibliography, https://dblp.org}
+}
 ```
 
 ## 🤝 Acknowledgements