Haoyu Gao — PhD Candidate at the University of Melbourne

Haoyu Gao

PhD Candidate · Software Engineering · University of Melbourne

I study how developers create, maintain, and communicate software knowledge — to each other and, increasingly, to AI agents.

Documentation Maintenance Software Ecosystems Human-AI Interaction Qualitative Methods ML for SE

CV Scholar GitHub Email ORCID

About Me

I am currently a fourth-year PhD student at the University of Melbourne (started from Jan 2023). I am supervised by A/Prof Christoph Treude and Dr. Mansooreh Zahedi.

My research intersects empirical and automated software engineering, focusing on improving how developers create, maintain, and use software documentation. I study documentation as a socio-technical artefact, combining repository mining, qualitative methods, and machine learning. With the rise of LLMs, my work is pivoting towards human–AI interaction, specifically examining how development knowledge is communicated to AI agents.

Before starting my Ph.D, I obtained my Master's degree in Information Technology from the University of Melbourne (WAM: 86.7/100), and my Bachelor's degree in Mathematics and Applied Mathematics from Fuzhou University, China.

News

Jul 2026 Paper accepted at EMSE — “AI Failures in the Eyes of the Downstream Developer: A First Look at Concerns, Practices, and Challenges” 📄
Jul 2026 New preprint on arXiv — “From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained” 📄
May 2026 Short paper accepted at MSR’26 — “On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source” 📄
Apr 2026 Attended ICSE’26 in Rio de Janeiro, Brazil 🇧🇷
Sep 2025 Visiting Postgraduate Research Student at Singapore Management University (Sep 2025 – Feb 2026) ✈️
Jun 2025 Paper accepted at ICSME’25 — “From Release to Adoption: Challenges in Reusing Pre-trained AI Models for Downstream Developers” 📄
May 2025 Paper accepted at ACL Findings’25 — “CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models” 📄
Mar 2025 Paper published in IEEE TSE — “Adapting Installation Instructions in Rapidly Evolving Software Ecosystems” 📄
Oct 2024 Presented at ESEM’24 on documenting ethical considerations in open source AI models 🎤

Publications

Published

MSR'26

On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source

H. Gao, P. Banyongrakkul, H. Guan, M. Zahedi, C. Treude

Short Paper in MSR'26: 23rd International Conference on Mining Software Repositories, 2026 (CORE A)

PDF arXiv

EMSE'26

AI Failures in the Eyes of the Downstream Developer: A First Look at Concerns, Practices, and Challenges

H. Gao, M. Zahedi, W. Jiang, H. Lin, J. Davis, and C. Treude

Empirical Software Engineering (Springer Nature), 2026 (CORE A)

PDF arXiv

ICSME'25

From Release to Adoption: Challenges in Reusing Pre-trained AI Models for Downstream Developers

P. Banyongrakkul, M. Zahedi, P. Thongtanunam, C. Treude, and H. Gao

ICSME'25: 41st International Conference on Software Maintenance and Evolution (CORE A)

PDF DOI

ACL Findings'25

CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models

H. Lin, C. Liu, H. Gao, P. Thongtanunam, and C. Treude

Findings of ACL'25: The 63rd Annual Meeting of the Association for Computational Linguistics (CORE A*)

PDF arXiv

TSE'25

Adapting Installation Instructions in Rapidly Evolving Software Ecosystems

H. Gao, C. Treude, and M. Zahedi

IEEE Transactions on Software Engineering, 2025 (CORE A*)

PDF DOI

ESEM'24

Documenting Ethical Considerations in Open Source AI Models

H. Gao, M. Zahedi, C. Treude, S. Rosenstock, and M. Cheong

ESEM'24: 18th International Symposium on Empirical Software Engineering and Measurement, 2024 (CORE A)

PDF DOI

FSE'23

Evaluating Transfer Learning for Simplifying GitHub READMEs

H. Gao, C. Treude, and M. Zahedi

ESEC/FSE'23: Proceedings of the Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2023 (CORE A*)

PDF DOI