Zhihao Lin

林智灏 (Zhihao Lin)

Ph.D. Student @ Beihang University

SMAT Laboratory | AI for Software Engineering

What's New

2026.07
把 squashed patch 重新组织成可 replay、可 review、可 selective revert 的原子提交历史。
2026.07
把 SKILL.md 约束与真实 agent 轨迹对齐,展示覆盖、违反、忽略路径,并生成 anti-bloat 优化建议。
2026.07
关于 LLM agents 能否真正修源码、拯救被生态漂移困住的旧仓库。
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
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), static analysis, and verifiable software-engineering environments to study reliable coding agents and ecosystem-specific toolchains.

Research Directions

I collaborate closely with Huawei on OpenHarmony quality and UI performance, Wei Ma at BTH on LLM code understanding and AI4SE 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

Coding AgentsProgram RepairExecution FeedbackRepo-Scale BenchmarksChange Impact AnalysisAtomic CommitsOpenHarmonyStatic AnalysisCode UnderstandingLow-resource Languages

🔬 Research Directions

Code AgentsProgram Repair

Coding Agents for Software Change

Measuring how coding agents choose context, execution, repository relations, and history organization when making real code changes.

  • Execution, static anchors, impact relations, and commit structure are measurable design choices
  • Process quality matters alongside final patch correctness
Representative Works
CodeAnchor (ISSTA 2026)To Run or Not to Run (ISSTA 2026)
4 methodsClick for details →
BenchmarksVerifiable SWE

Repository-Scale Benchmarks and Verifiable SWE Environments

Building low-leakage, execution-backed tasks where agents must repair, migrate, or rescue real repositories under observable constraints.

  • Whole-repository tasks expose failures that file-level benchmarks miss
  • Source-only checks, runtime blocking, and scenario validation make evaluation harder to game
Representative Works
To Run or Not to Run (ISSTA 2026)CodeAnchor (ISSTA 2026)
4 methodsClick for details →
OpenHarmonyDomain SE

OpenHarmony and Emerging-Language Toolchains

Building ecosystem-aware analysis, repair, migration, performance, and program-analysis infrastructure for OpenHarmony, ArkTS, and Cangjie.

  • From app repair and UI performance to Android migration and OpenHarmony-specific static analysis
  • Emerging ecosystems make domain knowledge, executable feedback, and low-resource adaptation central
Representative Works
HapRepair (FSE Industry 2025)Phantom Rendering Detection (FSE 2026)
4 methodsClick for details →
Code IntelligenceEvaluation

Code Understanding, Program Analysis, and AI4SE Measurement

Evaluating what LLMs understand about code and designing measurement protocols for AI-based SE tools and LLM-in-the-loop systems.

  • Capability claims should be tied to syntax, static behavior, dynamic behavior, and tool failure modes
  • Evaluation protocols need human audit, leakage control, and failure-mode analysis
Representative Works
Exploring Code Analysis (TOSEM 2026)Open-Source AI-based SE Tools (TOSEM 2024)
4 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 / AI4SE 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
  • MazeBreaker adaptive 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