CV

Hao Li is a Postdoctoral Researcher at Queen’s University (SAIL Lab and MCIS Lab), working on Agentic Software Engineering (AgenticSE), Software Engineering for AI (SE4AI), and software package ecosystems.

• Email: hao.li@queensu.ca
• ORCID: 0000-0003-4468-5972
• Google Scholar: scholar.google.com/citations?user=3xI3QLsAAAAJ
• GitHub: Leo-LiHao

Education

• Ph.D., University of Alberta, 2024 (Advisor: Cor-Paul Bezemer)

Research Positions

• Postdoctoral Researcher, Queen’s University — SAIL Lab & MCIS Lab, 2024–present (Advisors: Ahmed E. Hassan, Bram Adams)

Research Interests

• Agentic Software Engineering (AgenticSE)
• Software Engineering for Artificial Intelligence (SE4AI)
• Software Package Ecosystems

Publications

Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity

Do AI Coding Agents Log Like Humans? An Empirical Study

AIDev: Studying AI Coding Agents on GitHub

Can We Recycle Our Old Models? An Empirical Evaluation of Model Selection Mechanisms for AIOps Solutions

On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub

Towards Refining Developer Questions using LLM-Based Named Entity Recognition for Developer Chatroom Conversations

Mind the Merge: Evaluating the Effects of Token Merging on Pre-trained Models for Code

Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions

Beyond Blame: Rethinking SZZ with Knowledge Graph Search

Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers

An Empirical Study of Testing Practices in Open Source AI Agent Frameworks and Agentic Applications

Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models

SwarmUpdate: Hierarchical Software Updates and Deep Learning Model Patching for Heterogeneous UAV Swarms

Agent READMEs: An Empirical Study of Context Files for Agentic Coding

Agentic Refactoring: An Empirical Study of AI Coding Agents

HAFixAgent: History-Aware Automated Program Repair Agent

From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

A Systematic Literature Review of Software Engineering Research on Jupyter Notebook

Understanding Prompt Management in GitHub Repositories: A Call for Best Practices

Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality

Bridging the language gap: an empirical study of bindings for open source machine learning libraries across software package ecosystems

Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting

Agentic Software Engineering: Foundational Pillars and a Research Roadmap

The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering

An Empirical Study of Yanked Releases in the Rust Package Registry

Invited Talks

Agentic Software Engineering: The Rise of AI Teammates

June 10, 2026

Talk at Cisco DevNet, Virtual

Agentic Software Engineering: A Roadmap to Software Engineering 3.0

June 03, 2026

Tutorial at SEMLA 2026, Montreal, QC, Canada

Agentic Software Engineering: The Rise of AI Teammates

May 04, 2026

Talk at TruX Distinguished Seminar Series, Montreal, QC, Canada

Foundation Models and Software Engineering: Insights from Industry Blogs

November 03, 2024

Talk at AIware Leadership Bootcamp 2024, Toronto, ON, Canada

Academic Services

For a full list of organizing/program committee roles, editorships, and reviewing, see the About page.