Zhihao Lin

林智灏 (Zhihao Lin)

Ph.D. Student @ Beihang University

SMAT Laboratory | AI for Software Engineering

What's New

2026.06
Zhihao Lin*, Junhua Zhu*, Mingyi Zhou, Xin Wang, Zhensu Sun, Renyu Yang, David Lo, Li Li
2026.06
Zhihao Lin, Mingyi Zhou, Yizhuo Yang, Li Li
2026.04
Zhensu Sun*, Zhihao Lin*, Zhi Chen, Chengran Yang, Mingyi Zhou, Li Li, David Lo
2026.04
Zhihao Lin, Zhaofeng Liu, Mingyi Zhou, Zihan Huang, Chi Chen, Wei Ma, Li Li
2026.03
获得华为 AI 软件开发实习 Offer,计划开展 Android → HarmonyOS 迁移相关研究
2025.12
Zhihao Lin, Mingyi Zhou, Bo Sun, Han Hu, Gang Fan, Li Li
2025.06
Zhihao Lin, Wei Ma, Mingyi Zhou, Yanjie Zhao, Haoyu Wang, Yang Liu, Jun Wang, Li Li
2025.03
HapRepair: Learn to Repair OpenHarmony Apps — accepted at FSE Industry 2025
Zhihao Lin, Mingyi Zhou, Wei Ma, Chi Chen, Yun Yang, Jun Wang, Chunming Hu, Li Li
2025.01
我的第一篇文章 Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning 被 TOSEM 正式接收

About Me

I am a first-year Ph.D. student at Beihang University, working in the SMAT Laboratory under the supervision of Prof. Li Li (黎立), co-supervised by Mingyi Zhou (周鸣一).

My research focuses on AI for Software Engineering (AI4SE), combining Large Language Models (LLMs) with static analysis techniques to solve complex problems in software engineering.

Research Directions

I collaborate closely with Huawei on OpenHarmony quality and UI performance, Wei Ma at BTH on LLM code understanding and security evaluation, and Zhensu Sun at SMU on LLM coding agents and execution efficiency. My work has been published at top SE venues including ICSE, FSE, TOSEM, and EMSE.

Research Interests

Program RepairLLM SecurityStatic AnalysisCode GenerationOpenHarmonyJailbreak DefenseKnowledge GraphPrompt EngineeringLow-resource Languages

🔬 Research Directions

Code Intelligence

LLM Code Understanding

Investigating how LLMs comprehend code syntax and semantics for improved code analysis tasks.

  • What LLMs capture: syntax, flow cues, API intent
  • How to evaluate: benchmarks + probing + task metrics
Related Publications
Exploring Code Analysis (TOSEM 2026)CodeAnchor (ISSTA 2026)
3 methodsClick for details →
Fault Localization

Intelligent Code Localization

Enhancing bug localization accuracy by integrating static analysis with LLM-based agents.

  • Hybrid signal: static facts (graphs/flows) + LLM exploration
  • Goal: shrink search space and speed up debugging
Related Publications
CodeAnchor (ISSTA 2026)To Run or Not to Run (ISSTA 2026)
3 methodsClick for details →
Program RepairJournal Extension

OpenHarmony Defect Detection

Extending automated repair tools with new defect detection capabilities for the OpenHarmony ecosystem.

  • Build on HapRepair for OpenHarmony app quality
  • Defect detection rules for ArkTS/HarmonyOS APIs
Related Publications
HapRepair (FSE Industry 2025)Phantom Rendering Detection (FSE 2026)
3 methodsClick for details →
Impact Analysis

Change Impact Analysis

Leveraging code knowledge graphs to analyze and predict the impact of code changes across large codebases.

  • Model dependencies beyond files: symbols, calls, data edges
  • Predict ripple effects before merge / review
Related Publications
CodeAnchor (ISSTA 2026)Open-Source AI-based SE Tools (TOSEM 2024)
3 methodsClick for details →
Code Quality

Codebase Health Management

Exploring structured approaches to maintain codebase quality during iterative development.

  • Detect redundancy, dead code, and risky drift early
  • Make maintenance measurable and automatable
Related Publications
To Run or Not to Run (ISSTA 2026)Open-Source AI-based SE Tools (TOSEM 2024)
3 methodsClick for details →
Prompt Engineering

Prompt Robustness

Addressing prompt degradation issues caused by model updates and temporal drift.

  • Detect when prompts silently degrade after model updates
  • Automate prompt adaptation to keep behavior stable
Related Publications
MazeBreaker (ICSE 2026)
3 methodsClick for details →

Open-Source Tools

Accepted Papers (PDF)

View all →

To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair

ISSTA 2026

PDF

How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring

ISSTA 2026

PDF

Phantom Rendering Detection: Identifying and Analyzing Unnecessary UI Computations

FSE 2026

PDF

MazeBreaker: Multi-Agent Reinforcement Learning for Dynamic Jailbreaking of LLM Security Defenses

ICSE 2026

PDF

HapRepair: Learn to Repair OpenHarmony Apps

FSE Industry 2025

PDF

Effective Fine-tuning for Low-resource Languages: A Case Study of Cangjie

EMSE 2026

PDF

Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning

TOSEM 2024

PDF

Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs

TOSEM 2026

PDF

Collaborations

H
Huawei
OpenHarmony / mobile app quality
People and Works
Chi Chen
  • HapRepair: OpenHarmony app repair
  • Cangjie low-resource language fine-tuning
Han Hu
  • Phantom Rendering detection for mobile UI performance
Bo Sun
  • Phantom Rendering detection for mobile UI performance
Gang Fan
  • Phantom Rendering detection for mobile UI performance
Topics
  • OpenHarmony app repair
  • Phantom Rendering / UI performance analysis
  • Cangjie low-resource language fine-tuning
B
Blekinge Institute of Technology (BTH)
LLM code understanding / security evaluation
People and Works
Wei Ma
Associate Senior Lecturer, Blekinge Institute of Technology

Heartfelt thanks to Wei Ma for guiding me into research. When I first began, he patiently helped me with topic selection, paper reading, experiment design, and writing; much of my early research training was shaped by his guidance and support.

  • MazeBreaker: multi-agent RL for LLM jailbreak evaluation
  • HapRepair: LLM-guided repair for OpenHarmony apps
  • Exploring Code Analysis: syntax and semantic probing with LLMs
  • Open-source AI-based SE tools survey
Topics
  • LLM code understanding and semantic evaluation
  • LLM jailbreak and security evaluation
  • AI4SE open-source ecosystem studies
S
Singapore Management University (SMU)
LLM agents / execution efficiency
People and Works
Zhensu Sun
PhD candidate, Singapore Management University

Heartfelt thanks also to Zhensu Sun. After I became able to develop research ideas more independently, he continued to offer constructive advice on problem framing, experiment design, paper narrative, and limitation analysis, helping me learn how to refine early ideas into more complete and solid research work.

  • EAGER: executing code as LLMs generate it
  • To Run or Not to Run: execution cost-effectiveness in LLM repair agents
Topics
  • LLM coding agents
  • Execution cost and latency optimization
  • Code generation and program repair evaluation
我的音乐