Lihua Xu

Lihua Xu
Area Head of Computer Science, Professor of Practice in Computer Science, NYU Shanghai
Email
lx615@nyu.edu
Room
S752

Lihua Xu is the Area Head of Computer Science and a Professor of Practice in Computer Science at NYU Shanghai. She received her MS and PhD in computer science from the University of California, Irvine.

Her current work is on agentic systems, and on how software engineering — and the computer science curriculum more broadly — should be taught now that AI agents write much of the code. On the systems side, she studies how to design, build, and verify software that includes AI agents: agent architectures and workflows, tool use, guardrails and fallbacks, multi-agent decomposition, and how to evaluate whether an agentic system does what it is supposed to do. On the education side, she asks what must remain hard for students when AI can do the rest — in particular, how to tell whether students own their design decisions, can explain and defend them, and can verify what they and their agents build.

She was named a Shanghai Oriental Scholar in 2025, a municipal program that recruits and supports distinguished professors at Shanghai's universities, and received the 2026 NYU Shanghai Teaching Excellence Award, which recognizes innovative, reflective teaching that serves students in and beyond the classroom. Her earlier work on software analysis received the 2018 ACM SIGSOFT Distinguished Paper Award, and she received the Best New Investigator award at the 2006 Grace Hopper Celebration of Women in Computing.

Before turning to agentic systems, her research was in software engineering and mobile security, with a focus on improving software quality through program analysis and testing, published at ICSE, FSE, ASE, CCS, and MobiCom.

As Area Head, she leads the undergraduate computer science curriculum at NYU Shanghai and coordinates CS programs across NYU's New York, Shanghai, and Abu Dhabi campuses through the global CS Working Group.

Select Publications

  • Qingshun Wang, Lintao Gu, Minhui Xue, Lihua Xu, Wenyu Niu, Liang Dou, Liang He and Tao Xie, FACTS: Automated Black-box Testing of FinTech Systems, In Proc. ESEC/FSE, Industrial Track, 2018
  • Sen Chen, Ting Su, Lingling Fan, Guozhu Meng, Minhui Xue, Yang Liu, Lihua Xu, Are Mobile Banking Apps Secure? What Can be Improved?, In Proc. ESEC/FSE, Industrial Track, 2018
  • Lingling Fan, Ting Su, Sen Chen, Guozhu Meng, Yang Liu, Lihua Xu and Geguang Pu, Efficiently Manifesting Asynchronous Programming Errors in Android Apps, In Proc. ASE'18, Montpellier, France, 2018
  • Yujie Yuan, Lihua Xu, Xusheng Xiao, Andy Podgurski, and Huibiao Zhu, RunDroid: Recovering Execution Call Graphs for Android Applications. In Proc. ESEC/FSE, Demo Track, 2017
  • Wenqi Bu, Minhui Xue, Lihua Xu, Yajin Zhou, Zhushou Tang, and Tao Xie. When Program Analysis Meets Mobile Security: An Industrial Study of Misusing Android Internet Sockets. In Proc. ESEC/FSE, Industrial Track, 2017

 

Education

  • PhD, Information and Computer Science
    University of California, Irvine
  • MS, Information and Computer Science
    University of California, Irvine
Research Interests
  • Agentic system design and development: architectures, workflows, tool use, guardrails, multi-agent systems
  • Evaluation and verification of AI-assisted and agent-built software
  • Human–agent teaming in software development
  • AI in computer science education: AI learning companions, and assessing design ownership, communication, and verification skills
  • Software testing and program analysis
Courses Taught
  • Databases
  • Introduction to Computer Programming
  • Software Engineering