Lingzhi Yuan

Hi! I'm a Computer Science Ph.D. student at the University of Maryland, College Park, advised by Furong Huang.

My research spans three directions.

• Trustworthy Machine Learning. Aligning today's models and the agent systems they drive with human ethics, and making them run reliably in real-world environments.
• Self-evolving Agents. Designing mechanisms that let agents accumulate experience at deployment time, completing tasks better and at lower cost.
• Multi-agent Systems. Discovering collaboration patterns that let multiple relatively weak models jointly solve tasks a single strong model struggles with.

I obtained my B.Eng at Zhejiang University, majoring in Automation. I was also a research assistant at the Secure Learning Lab, University of Chicago, advised by Bo Li.

See my resume for more detail, or find the non-research side of me here 🧩.

Feel free to get in touch if any of this sounds interesting to you. lingzhiy@umd.edu (Click to copy)