About me
I am a second-year PhD candidate in the School of Computing and Information Systems, Faculty of Engineering and Information Technology, at The University of Melbourne.
My research focuses on measuring and understanding the emergence of frontier risks and evaluating the capabilities of AI agents in complex environments. I study how to ensure agent safety before deployment, during execution, and after task completion.
I am currently a research intern at Microsoft Research, working with Dr. Xiaoting Qin.
I am fortunate to be advised by A/Prof. Xingliang Yuan and Dr. Shaanan Cohney, and I also work closely with Dr. Feng Liu. Previously, during my masterβs degree, I conducted research in the TMLR Group, Melbourne, advised by Dr. Feng Liu.
I am always happy to discuss research and potential collaborations. Feel free to reach out at yuhaos1@student.unimelb.edu.au.
Research interests
- Agent safety
- Frontier risk evaluation
- Trustworthy machine learning
News
- Oct 2026 I joined Microsoft Research as a research intern, working with Dr. Xiaoting Qin.
- Jun 2026 Released our preprint TRIAD β From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents.
- Feb 2026 BiFTA was accepted to TMLR! π
- Jan 2026 Our paper on stealthy fine-tuning data extraction was accepted to ICLR 2026! π
- May 2025 SSNI was accepted to ICML 2025! π
Publications
You can also find my articles on my Google Scholar profile.




Education
- Ph.D. in Computer Science, The University of Melbourne β School of Computing and Information Systems, Faculty of Engineering and Information Technology Β· Aug 2025 β present
- M.S. in Information Technology (Artificial Intelligence), The University of Melbourne Β· Feb 2023 β Jun 2024 (with Distinction)
- B.S. in Computer Science, The University of Melbourne Β· Feb 2020 β Nov 2022
Academic service
- Reviewer, ICML, 2025, 2026
- Reviewer, ICLR, 2026
- Reviewer, TMLR
- Reviewer, Neural Networks
