|
|
|
| 🔍 Research Area | 📖 Description |
|---|---|
| 🧠 LLM Reasoning | Exploring the mechanisms and boundaries of LLMs in complex logical reasoning, covering areas such as Test-time Scaling and RL4LLM. |
| ⚙️ Auxiliary Policy Model | Integrating lightweight auxiliary policy models, trained via Reinforcement Learning, into LLM architectures to enhance model capabilities. |
| 🤖 MARL | Focusing on multi-agent system, including both LLM-based agents and traditional agents, to solve coordination and game-theoretic equilibrium. |
- I'm always open to collaboration and discussion on these topics.
- Email：b23042510@njupt.edu.cn ✅
- Feel free to reach out if you share similar interests or have exciting projects in mind!