Improve model card metadata

README.md

@@ -1,23 +1,21 @@
 ---
-license: apache-2.0
 language:
-  - en
+- en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 tags:
-  - large-language-model
-  - multi-agent-systems
-  - reinforcement-learning
-  - agentic-ai
-  - code
-  - math
+- large-language-model
+- multi-agent-systems
+- reinforcement-learning
+- agentic-ai
+- code
+- math
 ---
 
 # MetaAgent-X: Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning
 
-[Paper 📑](https://arxiv.org/abs/2605.14212)
-
-[Codebase 🚗](https://github.com/pettingllms-ai/PettingLLMs)
-
-[Project Page 🏆](https://mercury7353.github.io/MetaAgent-X-Page/)
+[Paper 📑](https://arxiv.org/abs/2605.14212) | [Codebase 🚗](https://github.com/pettingllms-ai/PettingLLMs) | [Project Page 🏆](https://mercury7353.github.io/MetaAgent-X-Page/)
 
 ## Overview
 
@@ -50,7 +48,7 @@ Numbers in parentheses denote absolute gains over the single-agent baseline.
 | Overall | Average | **38.33** |
 
 ## Citation
-```
+```bibtex
 @misc{zhang2026metaagentxbreakingceiling,
       title={MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning}, 
       author={Yaolun Zhang and Yujie Zhao and Nan Wang and Yiran Wu and Jiayu Chang and Yizhao Chen and Qingyun Wu and Jishen Zhao and Huazheng Wang},