avatar

ZHAO Huan

Ph.D. Candidate
National University of Singapore
zhaohuan (at) comp.nus.edu.sg


About Me

I am a Ph.D. student in the School of Computing at the National University of Singapore (NUS), where I am fortunate to be advised by Provost’s Chair Professor Abhik Roychoudhury and Presidential Young Professor Umang Mathur. Prior to that, I obtained my Bachelor degree (first-class honours) also from NUS in 2023.

I am generally interested in understanding and enhancing the trustworthiness of modern software, especially in the algorithmic aspects of automated testing and verification technologies. My work explores different techniques on the spectrum, including agentic, symbolic, and randomized approaches. I am currently looking into how AI agents can leveage existing formal machinery to reason confidently and reliably about code.

Recent News

Publications

  1. [FSE'26] Agentic Verification of Software Systems Code
    Haoxin Tu, Huan Zhao, Yahui Song, Mehtab Zafar, Ruijie Meng, Abhik Roychoudhury
    34th ACM International Conference on the Foundations of Software Engineering (FSE), 2026.
    [One-line Summary] Can LLM agents write formal proofs for program verification tasks?

  2. [S&P'26] Agentic Concolic Execution Code Slides BibTex
    Zhengxiong Luo, Huan Zhao, Dylan Wolff, Cristian Cadar, Abhik Roychoudhury
    47th IEEE Symposium on Security and Privacy (S&P), 2026.
    [One-line Summary] The first language- and theory-agonistic symbolic executor, empowered by LLM agents.

  3. [ASPLOS'25] Selectively Uniform Concurrency Testing Code Slides BibTex
    Huan Zhao, Dylan Wolff, Umang Mathur, Abhik Roychoudhury
    30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2025.
    [One-line Summary] Exposing concurrency bugs with optimal probabilistic guarantees via random testing.

Academic Services