Professional Summary
Hailin Liu is a PhD researcher in Artificial Intelligence and Machine Learning,
focusing on Agentic AI, Multi-Agent Systems, and AI Security. His research
explores runtime governance mechanisms for autonomous intelligent systems,
including agent safety, long-horizon reasoning, and adaptive control.
Education
PhD in Artificial Intelligence and Machine Learning
Oct 2026
Present
Master in Applied Mathematics and Computer Science (with Honours)
Sep 2024
Jun 2026
Bachelor in Fundamental Informatics and Information Technology
Sep 2020
Jun 2024
Interests
Agentic AI
Multi-Agent Systems
Runtime Governance
AI Security
Trustworthy AI
Large Language Models
🔬 My Research
My research focuses on runtime governance and security mechanisms for autonomous agent systems.
I study Agentic AI, Multi-Agent Systems, and trustworthy AI, with particular interests in agent safety, adaptive control, and long-horizon autonomous execution.
My current research direction explores how intelligent agents can be governed and secured during execution.
Publications & Preprints
Conference Contributions