Minghao (Mark) Liu 刘明昊

About Me

I completed my undergraduate studies at the Hong Kong University of Science and Technology (HKUST), majoring in Computer Science with a minor in Mathematics. I will continue at HKUST as a PhD student from Fall 2026, supported by the Hong Kong PhD Fellowship Scheme (HKPFS).

My research interests lie in Natural Language Processing (NLP) and agentic reasoning, with a focus on building interpretable, reliable, and high-performing AI systems. Specifically, I am interested in:

1. Developing interpretable methods to guide model behavior and enhance reliability in real-world applications.
2. Diagnosing the limitations of current language models through explainable and systematic benchmarking.
3. Designing dynamic, scalable learning environments and robust evaluation metrics to enable LLM agents to learn, reason, and perform beyond human-level competence.
4. Developing Deep Research Agents, with an emphasis on efficiently constructing effective experience trajectories that enable reasoning using both internal knowledge and web-integrated information.

I also have experience in formal language (e.g., Lean) and neural circuit modeling.

Education

• BEng in Computer Science | Minor in Mathematics
  Hong Kong University of Science and Technology (HKUST), Hong Kong SAR | 2022 – 2026 (Expected)
  CGA: 3.902 / 4.3 (Top 2%)


• Exchange Student
  McKelvey School of Engineering, Washington University in St. Louis | Fall 2024
  GPA: 3.94 / 4.00

Publications

Activities