Jiayuan Zhou

I am a Senior Principal Researcher at the Waterloo Research Center, Huawei Canada. Every software artifact (e.g., commits, issues, agent trajectories) records what was done, but rarely why. My team learns the why and puts it to work:

• Process intelligence for coding agents. We mine historical issues, agent trajectories and test outcomes into constraints and guidance for the next run. Our work Lingxi received an ISSTA’26 Distinguished Paper award. More details →
• Proactive vulnerability sensing for open source. We detect silent fix commits 1–2 weeks before public disclosure, a window that LLM-built exploits now close in days, then assess, fix and validate them within that window. More details →

I received my Ph.D. in Computer Science from the SAIL lab, Queen’s University, under the supervision of Prof. Ahmed E. Hassan and Prof. Shaowei Wang. My dissertation studied extrinsic incentives in open source communities through mining GitHub, Stack Overflow, and Bountysource data. Before grad school, I was the founding engineer of 1688’s One-Click Dropshipping (一键代销) system at Alibaba Group — a full-stack platform connecting B2B suppliers with millions of Taobao/Tmall merchants.

Research interests: AI agents for software engineering, experience and procedural knowledge mining, agent trajectory analysis, test-time scaling, agent evaluation, vulnerability detection and management, mining software repositories.

Publications: papers at ICSE, FSE, ASE, ISSTA, IEEE TSE, ACM TOSEM, and EMSE — see publications and google scholar. I hold 12 patents in software engineering and AI applications.