Improve model card: Add description, paper and code links

This PR improves the model card by adding a description of the GTAlign model, a link to its paper ([GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare](https://huggingface.co/papers/2510.08872)), a link to the corresponding GitHub repository ([https://github.com/ulab-uiuc/GTAlign](https://github.com/ulab-uiuc/GTAlign)), and a link to the project page ([https://huggingface.co/GTAlign](https://huggingface.co/GTAlign)).

The existing metadata for `license`, `library_name`, `pipeline_tag`, `base_model`, `language`, and `tags` remains unchanged as it is already comprehensive.

Please review and merge if everything looks good!

README.md

@@ -1,11 +1,19 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-3B-Instruct
-pipeline_tag: text-generation
+language:
+- en
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - agent
----
+---
+
+# GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare
+
+GTAlign is an alignment framework that integrates game-theoretic decision-making into both reasoning and training of LLM assistants, encouraging them to make decisions that are not only accurate but also rational, cooperative, and transparent.
+
+- 📄 Paper: [GTAlign: Game-Theoretic Alignment of LLM Assistants for Mutual Welfare](https://huggingface.co/papers/2510.08872)
+- 💻 Code: [https://github.com/ulab-uiuc/GTAlign](https://github.com/ulab-uiuc/GTAlign)
+- 🌐 Project Page: [https://huggingface.co/GTAlign](https://huggingface.co/GTAlign)