Title: Building and Stress-Testing Robust AI Agent Systems for Real-World Deployment
Date: Thursday, Oct 29th, 2026
Time: 13:00 - 15:00 PM EDT
Location: Online
Zoom: https://gatech.zoom.us/j/5256702657?pwd=bWyj8saWbSVdLlrhb7PEHJYlZ5bTO5.1
Yanzhe Zhang
Ph.D. Student in Computer Science
School of Interactive Computing
Georgia Institute of Technology
https://stevenyzzhang.github.io/website/
Committee members
Dr. Diyi Yang (advisor) - Computer Science Department, Stanford University
Dr. Zsolt Kira (co-advisor) - School of Interactive Computing, Georgia Institute of Technology
Dr. Kartik Goyal - School of Interactive Computing, Georgia Institute of Technology
Dr. Polo Chau - School of Computational Science & Engineering, Georgia Institute of Technology
Dr. Sanmi Koyejo - Computer Science Department, Stanford University
Abstract
Large language models (LLMs) are rapidly evolving from passive text generators into autonomous, multimodal agents that can perceive, reason, and act in the real world. This transformation unlocks new capabilities, while also reshaping human-AI interaction and introducing new risks. In this thesis, I present my research on building and stress-testing robust AI agent systems for real-world deployment. First, I introduce methods for building and evaluating agents with new capabilities, including automatically generating webpages from visual designs and generative interfaces that structure user interaction with AI systems. Second, I audit adversarial risks in these agents, showing that computer-use agents are vulnerable to pop-up attacks, and that simulation-driven search can systematically uncover privacy attacks and defenses in agent-agent communication. Third, I show that risks can emerge even without any adversary: task-irrelevant context silently flips individual predictions while aggregate accuracy barely changes, and agents that collaborate over long horizons can spontaneously collude to bypass the verification protocols they are asked to follow. Together, these results contribute to building AI agents that are both more capable in serving users and more trustworthy when deployed at scale.