Human-centered AI agency

I help people see, understand, and correct misalignments in AI privacy and security.

I am a Postdoctoral Fellow in the Department of Computer Science at Johns Hopkins University, advised by Dr. Yaxing Yao. I received my Ph.D. in Computer Science and Engineering from the University of Notre Dame in 2026, advised by Dr. Toby Jia-Jun Li and Dr. Yanfang Ye. My research lies at the intersection of human-computer interaction, usable privacy and security, and LLM and computer-use agents. I design empirical methods and interactive systems that evaluate AI agents across privacy, security, reliability, and human-oversight risks, from contextual privacy scaffolds to experiential auditing tools and oversight mechanisms for autonomous agents.

Research Overview
01

Agent auditing

Evaluating and auditing AI agents at scale

I run large-scale behavioral analyses of real-world coding, GUI, and tool-use agent sessions, and build benchmarks that reveal the gap between clean-task performance and failure-aware, trustworthy behavior.

02

Privacy & security scaffolds

Making AI-driven decisions transparent and contestable

I design interaction scaffolds and experiential auditing tools that surface privacy- and security-relevant signals at the right moment, turning opaque AI inferences into concrete, inspectable, and correctable outcomes.

03

Human oversight

Designing oversight mechanisms for autonomous agents

I study adversarial interfaces, dark patterns, and oversight strategies for computer-use agents, building interfaces and evaluation frameworks that let people catch and correct unsafe agent behavior.

News
Selected Publications

* indicates equal contribution.

Image for NARRA-Gym for Evaluating Interactive Narrative Agents
NeurIPS 2026

NARRA-Gym for Evaluating Interactive Narrative Agents

Yue Huang, Yuchen Ma, Jiayi Ye, Wenjie Wang, Zipeng Ling, Xingjian Hu, Yuexing Hao, Zichen Chen, Zhangchen Xu, Yunhong He, Zhengqing Yuan, Yujun Zhou, Kehan Guo, Chaoran Chen, Toby Jia-Jun Li, Stefan Feuerriegel, Xiangliang Zhang

[Paper PDF]