Introduction

I am Jiaqi Liu, a prospective Ph.D. candidate jointly supervised by Zhejiang University and China Telecom’s AI Institute (TeleAI), under the guidance of Professor Jian Zhao (TeleAI) and Professor Zhibo Wang (ZJU).

My research focuses on Agent Safety, covering the security of the underlying model, the safety of memory mechanisms, and the safety of tool-use. We aim to explore how to build the next generation of intelligent agents that are reliable, controllable, and trustworthy. Researchers interested in agent safety are welcome to reach out for discussion and collaboration as we advance this field together.

Education

• 2022 – 2026(expected)
  Zhejiang University
  Bachelor of Engineering in Automation

• 2026 – (expected)
  Zhejiang University ⨯ TeleAI (Joint Program)
  Ph.D. Candidate in Electronic and Information Engineering

Publications

under construction……