Yaxin Ma

I'm a Ph.D. student in Electrical & Computer Engineering at the University of Florida, advised by Prof. Jose C. Principe and Prof. Alina Zare. I work on trustworthy LLMs and agents — evaluating them, quantifying their uncertainty, and building systems reliable enough to act on their own.

I like working at the boundary between research and engineering: designing a method, then turning it into a system that actually runs. Recently that has meant autonomous coding agents; earlier it meant EEG brain–computer interfaces, medical image segmentation, and out-of-distribution detection. The throughline is reliability — I care less about what a model outputs than about whether it knows when it might be wrong.

This site collects what I'm building and thinking about:

• Projects — open-source systems and research work.
• Articles — an evolving set of notes and essays on how agents reason: planning, tool use, reflection, and the gap between what an agent does and what it can explain.

Research interests

• Trustworthy LLMs & agents
• LLM & agent evaluation
• Uncertainty quantification & out-of-distribution detection