Quanzhi Fu

About Me

I am a Ph.D. student in Computer Science at Virginia Tech, advised by Prof. Dan Williams, researching system infrastructure for the age of AI agents. My current work explores how operating systems and cloud infrastructure must evolve to support the demands of autonomous agent workloads. Previously, I contributed to container network core modules at Alibaba Cloud and conducted visiting research at Carnegie Mellon University.

I am a founding member of AgentsZone, a practitioner community dedicated to agent-driven software development. I am also the lead author of High-Quality Delivery: 100x Productivity with AI Agents, a systematic framework for agent-driven software engineering drawn from the practices of hundreds of real-world practitioners.

I closely follow the latest research in AIOps and agent infrastructure, and occasionally write about what I find. Check out my blog.

News

• [Mar. 2026] New blog post: System Infrastructure for the Agent Era: Recap of the First AgenticOS Workshop.
• [Mar. 2026] Our paper AgentCgroup received the Best Paper Award at AgenticOS 2026!
• [Mar. 2026] New blog post: Agent Management: The Deterministic Boundaries of AI Coding.
• [Mar. 2026] I am presenting our paper on LLM-driven WAF rule generation at AgenticOS 2026 on March 23. See you in Pittsburgh!
• [Mar. 2026] Our work AgentCgroup: Understanding and Controlling OS Resources of AI Agents is accepted at AgenticOS 2026.
• [Feb. 2026] New blog post: End-to-End Evolution for Unknown Failures: CloudMate’s Adaptive Path Exploration.
• [Jan. 2026] New blog post: How AIOps Systems Should Evolve with Software: Lessons from CloudMate.
• [Dec. 2025] New blog post: Will LLMs Disrupt Traditional Operations? A Survey of AI-Driven Ops.
• [Aug. 2024] Ph.D. study at Virginia Tech begins!

Publications

Quanzhi Fu and Dan Williams. “Toward LLM-Driven Rule Generation for Enforcement Systems: An Exploratory Study on WAF.” AgenticOS 2026.

Yusheng Zheng, Jiakun Fan, Quanzhi Fu, Yiwei Yang, Wei Zhang, and Andi Quinn. “AgentCgroup: Understanding and Controlling OS Resources of AI Agents.” AgenticOS 2026.

Lingxiang Wang, Quanzhi Fu, Wenjia Song, Gelei Deng, Yi Liu, Dan Williams, and Ying Zhang. “SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis.” arXiv, arXiv:2506.17798, 2025.

Quanzhi Fu, Qiyu Wu, and Dan Williams. “Mining the Gold: Student-AI Chat Logs as Rich Sources for Automated Knowledge Gap Detection.” arXiv, arXiv:2512.22404, 2025.

Xuan Mai, Quanzhi Fu, and Yi Chen. “Packet Routing with Graph Attention Multi-Agent Reinforcement Learning.” 2021 IEEE Global Communications Conference (GLOBECOM), 2021.

Background

Experience

• Infrastructure Engineer Intern, Alibaba Cloud, Summer 2023

Education

• Ph.D. in Computer Science, Virginia Tech, 2024–present
  • Advised by Prof. Dan Williams
• MEng in Electrical and Computer Engineering, Duke University & Duke Kunshan University, 2022–2024
• BSc in Statistics (Data Science track), the Chinese University of Hong Kong, Shenzhen, 2018–2022

Teaching

I LOVE TEACHING! I have been a teaching assistant for 3 courses and been named “THE BEST TA EVER” by multiple undergraduate students.

• Teaching Assistant, INFOSCI102 Computation and Problem Solving, Duke Kunshan University, Spring 2023
  • Developed Final Project and Autograder for the course
• Teaching Assistant, STATS101, Intro. Apply Statistical Method, Duke Kunshan University, Fall 2022
  • Developed an R Tutorial for Absolute Beginners
• Teaching Assistant, STA4001, Stochastic Processes, the Chinese University of Hong Kong, Shenzhen, Spring 2022

Misc.

• I am a certified personal trainer accredited by the Chinese Fitness and Bodybuilding Association 🏋🏻

• Over three years experience in practicing boxing and kickboxing 🥊

Powered by Jekyll and Minimal Light theme.