Create OpenMLRL organization card from the official website

README.md

@@ -1,10 +1,33 @@
 ---
-title: README
-emoji: 📉
-colorFrom: purple
-colorTo: purple
+title: OpenMLRL
+emoji: 🤝
+colorFrom: blue
+colorTo: indigo
 sdk: static
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# OpenMLRL
+
+### Multi-LLM Reinforcement Learning
+
+We build open-source frameworks and tools for training language models to work together. Our research explores cooperative reinforcement learning, preference learning, multi-turn interaction, and decentralized multi-agent systems.
+
+[Website](https://openmlrl.github.io/) · [GitHub](https://github.com/OpenMLRL) · [Research](https://openmlrl.github.io/research/) · [Contact](mailto:liu.shuo2@northeastern.edu)
+
+## CoMLRL
+
+[Cooperative Multi-LLM Reinforcement Learning (CoMLRL)](https://github.com/OpenMLRL/CoMLRL) is our library for training teams of language models with multi-agent reinforcement learning. It provides policy-gradient, actor-critic, and preference-based methods, with support for decentralized agents and centralized alternatives.
+
+[Read the documentation](https://openmlrl.github.io/CoMLRL/) · [Explore the code](https://github.com/OpenMLRL/CoMLRL)
+
+## Environments
+
+- **[Writing](https://github.com/OpenMLRL/LLM_Collab_Writing)** — Collaborative summarization and article writing.
+- **[Coding](https://github.com/OpenMLRL/LLM_Collab_Code_Generation)** — Cooperative code generation.
+- **[Travel](https://github.com/OpenMLRL/LLM_Collab_Travel)** — Travel planning under user constraints.
+- **[Tool Use](https://github.com/OpenMLRL/LLM_Collab_BFCL)** — Collaborative function calling with BFCL v4.
+
+## Get involved
+
+Explore our [datasets](https://huggingface.co/OpenMLRL/datasets), read our [research](https://openmlrl.github.io/research/), or contribute through [GitHub](https://github.com/OpenMLRL). For research inquiries, contact [liu.shuo2@northeastern.edu](mailto:liu.shuo2@northeastern.edu).