About me

I am a PhD student at the University of California, Santa Barbara, advised by Prof. Xifeng Yan. I have extensive research experience in conversational AI and have participated in the development and research of intelligent customer service chatbots for several major companies. My research focuses on exploring the interaction between conversational AI and humans, as well as developing more effective and intelligent conversation systems.

Recent News

I have developed a multi-agent development framework, MICA (Multiple Intelligent Conversational Agents), which establishes a standardized, simple, and efficient protocol for rapidly building multi-agent chatbots. MICA proposes its own solution for the future of multi-agent chatbots, exploring interactions among multiple agents while continuously evolving toward more advanced chatbot architectures.

The code is now open-source—feel free to use it! You can find the repository here. For more details, please refer to the documentation here.

Publications

• Learning to Lie: Adversarial Attacks Driven by Reinforcement Learning Damage Human-AI Teams and LLMs (Accepted, Workshop on ICLR 2025)

Teaching

[UCSB] CS165A: Artificial Intelligence, Teaching Assistant, Spring 2024 & Fall 2024. [Course Website]