ACADEMIC HOMEPAGE
Hui Zhang
I hold a master’s degree in Applied Statistics from Beijing Institute of Technology. I study how language-model agents learn from experience, use external knowledge, and make reliable decisions over extended interactions. My recent work connects clinical-agent evaluation, regression-safe knowledge routing, audits of LLM judges, and exact feedback reduction for model comparison. Drawing on statistics, I aim to develop agents that improve over time and evaluation methods that make their progress measurable, trustworthy, and efficient.
RESEARCH
Research interests
My long-term research goal is to build language-model agents that learn reliably from interaction, supported by statistically grounded and resource-efficient evaluation. I am particularly interested in the connection between agent learning, feedback quality, and the evidence needed to establish real improvement.
- Continual learning and agent memory — How can agents turn interaction traces into useful experience, transfer it to new tasks, and retain earlier capabilities through updates?
- Reliable reasoning and knowledge use — When should an agent seek evidence, consult another agent, or revise its answer? I study adaptive routing and decision rules that improve reasoning while limiting regressions.
- LLM judges and human feedback — How can evaluation distinguish verifiable errors, stable human preferences, and genuine disagreement? I am interested in judge reliability, preference calibration, and long-horizon creative tasks.
- Efficient statistical evaluation — How can model comparisons use less feedback without losing the information needed for valid conclusions? My interests include exact estimation, uncertainty, coupled sampling, and evaluation during model updates.
PUBLICATIONS
Papers
Learning When to Trust Medical Knowledge: Regression-Safe Routing for Clinical Reasoning
AAAI submission · Under reviewDramaGrow: A Regime-Aware Benchmark for Auditing LLM Judges of Multi-Episode Drama
AAAI submission · Under reviewPay for the Difference: Exact Feedback Reduction for Language Model Comparison
ICLR submission · Under reviewA novel composite of Closed-Cell aluminum foam and Phase-Change material for enhanced mechanical safety in EV battery systems
Composite Structures · 2025NOTES
Blog
PROFILES