I am a CS PhD student in LLM agents Imperial College London with Marek Rei. That's my latest work: StateAct, which outperforms ReAct by ~10%.
I work on:
- 🧠 LLM Reasoning
- 🛠️ LLMs + Tools
- 🤖 LLM agents
Specifically, investigating 🔭:
- How to acquire new skills (automatically) for LLM Agents.
- How to make LLM agents follow instructions better (fine-tuning, RAG, ++).
- How to help LLM agents recover from mistakes.
Get in touch with me:
- 📫 via email.
- 🌱 to collaborate.
