Hi there! I am a leading explorer on fundamental agentic research at Qwen Team.
Some topics I am interested in include
- code/tool centric agentic rl (collaborative/adversarial training)
- context/memory rl (online learning)
- environment alignment (self-evolve and scaling algorithms)
I am happy to chat and discuss potential collaborations, feel free to reach out by
🌟 Studying Zone
(2025.06) My thought about agentic rl training.
(2024.09-) I joined Qwen Team as a researcher 🥝!
(2024.01-) I am part-time collaborating with Cornell ICPC and Millennium to build LLMs for code and data generation.
- This work is called ALICE (Aligning Language models for Interactive Code Execution), find more about it at alicellm.github.io.
- ALICE is a meta-agent collaboration system that generates high-quality data through multi-turn interactions and feedback without human intervention.
- It produces multimodal data with traces from agent strategies like ReAct and Reflexion, which are scarce but offer potential for aligning advanced LLMs.
(2023-2024) I I led the prior work of ALICE called Voice2Action with Cornell XRC, an Unity Package for real-time code execution in VR; and studied on large-scale generation augmented retrieval systems (opposed to RAG) at Cornell NLP.
(2021-2022) I interned on graph machine learning at AWS AI Lab and contributed to the open source Deep Graph Library.
👀 Chilling Zone
I like programming! I lead the "Cornell Tech" Group at Cornell ICPC and won the Top 20% in 2023 Regional!
I enjoy cooking, listening to music of all forms, playing ping-pong, reading science fiction, and more!
⚡ Developing Zone
