Beyond Static Alignment: Advancing Trustworthy and Socially Intelligent AI Agents

Speaker: Dr. Jieyu ZHAO
University of Southern California

Title: Beyond Static Alignment: Advancing Trustworthy and Socially Intelligent AI Agents

Date: Tuesday, 3 March 2026

Time: 3:00pm to 4:00pm

Venue: Lecture Theater G
(Chow Tak Sin Lecture Theater), near lift 25/26, HKUST

Abstract:

Large language models have transformed how we interact with technology, but most deployed systems remain reactive and rely on static, one-size-fits-all alignment, limiting trust in real-world, high-stakes settings. This talk explores a path toward personalized, trustworthy AI assistants that can reason, continually adapt, and align with user values while remaining safe and socially appropriate. I will introduce Computer-Using Agents that combine GUI operations and code generation to efficiently complete real-world tasks, and present CoAct-1, a multi-agent system that coordinates planning and execution. I will then discuss SEA, a black-box auditing algorithm for uncovering LLM knowledge deficiencies and probing failure modes such as hallucination under limited query budgets. Next, I will present WildFeedback, a framework that learns in-situ user preferences from natural, multi-turn interactions, enabling continual personalization beyond lab-style preference data. Finally, I will highlight ongoing work on proactive social intelligence and culturally grounded evaluation, spanning intention understanding, reasoning consistency, and value-aligned collaboration. Together, these advances move us closer to AI systems that don’t just respond, but adapt responsibly and assist people in ways that are reliable, equitable, and context-aware.

Biography:

Jieyu Zhao (https://jyzhao.net) is a Gabilan Assistant Professor in the Thomas Lord Department of Computer Science at the University of Southern California, where she leads the LIME Lab. Prior to joining USC, she was an NSF Computing Innovation Fellow at the University of Maryland, College Park, working with Prof. Hal Daum? III. She earned her Ph.D. in Computer Science from UCLA under the supervision of Prof. Kai-Wei Chang. Her research focuses on trustworthy language models and human-centered AI, with an emphasis on building AI systems that are reliable, socially responsible, and aligned with human values. Her work has been recognized with multiple honors, including the EMNLP Best Long Paper Award (2017), an SAC Highlight Award (EMNLP 2025), and a Top-10 Most Cited Paper distinction (NAACL 2018). Her research has received widespread media coverage, including features in Wired, The Daily Mail, VentureBeat, MarkTechPost, etc. She was invited by UN Women in Beijing and Korea to speak on gender equality and social responsibility in AI. She is a recipient of the 2020 Microsoft PhD Fellowship, was selected for the 2021 Rising Stars in EECS workshop, and was named one of the “100 Women in AI Ethics” in 2025.