About Me

I am a Ph.D. candidate in the Department of Computer Science at Purdue University, advised by Prof. Xiangyu Zhang since 2021. Before that, I received my Bachelor’s degree in Computer Science and Technology from Huazhong University of Science and Technology in 2020.

My research focuses on improving software reliability and efficiency. I build LLM agents or program analysis tools to automate software development tasks such as code generation, software testing, and program repair, with the broader goal of improving software correctness, robustness, and trustworthiness. Currently, I focus on building more reliable and effective LLM coding agents.

Experience

Applied Science Intern @ AWS, Agentic AI, Kiro Science
Santa Clara, CAAug. 2025 – Nov. 2025
Project: Context Optimization for LLM Coding Agent

Research Intern @ Microsoft Research, RiSE Group
Redmond, WAMay 2025 – Aug. 2025
Project: LLM Agent for Semantic Testing of Software Systems

Research Intern @ Microsoft Research, RiSE Group
Redmond, WAMay 2024 – Dec. 2024
Project: LLM Agent for Refactoring Network Protocol Code with Verified Parsers

Publication

PR²: Peephole Raw Pointer Rewriting with LLMs for Translating C to Safer Rust
Yifei Gao, Chengpeng Wang, Pengxiang Huang, Xuwei Liu, Mingwei Zheng, Xiangyu Zhang
Findings of ACL 2026

NESA: Relational Neuro-Symbolic Static Program Analysis
Chengpeng Wang, Yifei Gao, Wuqi Zhang, Xuwei Liu, Jinyao Guo, Mingwei Zheng, Qingkai Shi, Xiangyu Zhang
FSE 2026

SFA-Miner: Mining Path-Sensitive API Usage Patterns via Symbolic Finite Automata
Jiasheng Jiang, Mingwei Zheng, Qingkai Shi, Xiangyu Zhang
S&P 2026

RFCAudit: AI Agent for Auditing Protocol Implementations Against RFC Specificationss
Mingwei Zheng, Chengpeng Wang, Xuwei Liu, Jinyao Guo, Shiwei Feng, Xiangyu Zhang
ASE 2025

CORE: Benchmarking LLMs’ Code Reasoning Capabilities through Static Analysis Tasks
Danning Xie*, Mingwei Zheng*, Xuwei Liu, Jiannan Wang, Chengpeng Wang, Lin Tan, Xiangyu Zhang
* Equal contribution, Spotlight (56 out of 497 accepted papers)
NeurIPS 2025, Datasets and Benchmarks Track

IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents
Shiwei Feng, Xiangzhe Xu, Xuan Chen, Kaiyuan Zhang, Syed Yusuf Ahmed, Zian Su, Mingwei Zheng, Xiangyu Zhang
NeurIPS 2025

Validating Network Protocol Parsers with Traceable RFC Document Interpretation
Mingwei Zheng, Danning Xie, Qingkai Shi, Chengpeng Wang, Xiangyu Zhang
ISSTA 2025

Large Language Models for Validating Network Protocol Parsers
Mingwei Zheng, Danning Xie, Xiangyu Zhang
LangSec 2025

ParDiff: Practical Static Differential Analysis of Network Protocol Parsers
Mingwei Zheng, Qingkai Shi, Xuwei Liu, Xiangzhe Xu, Le Yu, Congyu Liu, Guannan Wei, Xiangyu Zhang
🏆 ACM SIGPLAN Distinguished Paper Award (7 out of 148 accepted papers)
OOPSLA 2024

Lifting Network Protocol Implementation to Precise Format Specification with Security Applications
Qingkai Shi, Junyang Shao, Yapeng Ye, Mingwei Zheng, Xiangyu Zhang
CCS 2023

Why Do Developers Remove Lambda Expressions in Java?
Mingwei Zheng, Jun Yang, Ming Wen, Hengcheng Zhu, Yepang Liu, Hai Jin
ASE 2021

Preprint

Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent
Zhou Xuan, Xiangzhe Xu, Mingwei Zheng, Louis Zheng-Hua Tan, Jinyao Guo, Tiantai Zhang, Le Yu, Chengpeng Wang, Xiangyu Zhang
arXiv:2602.06325, 2026

Honors and Awards

  • Graduate Teaching Award, Spring 2026
  • WISP Graduate Travel Grant, Fall 2025
  • Spotlight Paper, NeurIPS 2025 (Datasets and Benchmarks Track)
  • ACM SIGPLAN Distinguished Paper Award, OOPSLA 2024
  • Outstanding Graduate, Huazhong University of Science and Technology (HUST), 2020

Invited Talks

  • Semantic Bug Detection for Secure Network Protocol Implementations
  • An LLM Agent for Functional Bug Detection in Network Protocols
  • ParDiff: Practical Static Differential Analysis of Network Protocol Parsers
    • iSE, University of Illinois Urbana-Champaign, Nov. 2024
    • LangSec Workshop, May 2024

Service

Teaching

  • Teaching Assistant, CS 18200: Foundations of Computer Science — Spring 2026
  • Teaching Assistant, CS 18000: Problem Solving and Object-Oriented Programming — Spring 2022
  • Teaching Assistant, CS 30700: Software Engineering — Fall 2022