Profile

I am a first-year PhD student in software engineering. My research interests include software testing, refactoring, bug prediction, and Agentic Software Engineering, with the goal of improving software quality and development efficiency.
In particular, I focus on empirical analysis of how refactoring affects test code quality and maintainability, and on evaluating the effectiveness of AI agents in software development.

I believe we are approaching an era where AI agents will autonomously develop software.
At the same time, agent-induced system failures have already been reported, making it critical to establish quality assurance for the agent era.
Through the development of next-generation bug prediction and testing techniques, I am working to build the “foundation of reliability” that underpins agent-driven development.

International Research Experience:

• Visiting Student, Queen’s University SAIL & MCIS Lab (Canada, Sep – Nov 2025)
• Visiting Student, Hangzhou Dianzi University (China, Jun – Jul 2025)
• Visiting Student, Radboud University (Netherlands, Sep – Nov 2024)
  
  

Major Publications

Peer-Reviewed Conference Papers

• How Does Test Code Differ From Production Code in Terms of Refactoring? An Empirical Study
  Kosei Horikawa, Yutaro Kashiwa, Bin Lin, Kenji Fujiwara, Hajimu Iida
  The 41st International Conference on Software Maintenance and Evolution (ICSME 2025 NIER Track). [CORE A]

• An Empirical Investigation into Maintenance of Load Testing Scripts
  Ibuki Nakamura, Kosei Horikawa, Brittany Reid, Yutaro Kashiwa, Hajimu Iida
  The ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM 2025 ERVT Track). [CORE A]

• Do AI Agents Really Improve Code Readability?
  Kyogo Horikawa, Kosei Horikawa, Yutaro Kashiwa, Hidetake Uwano, Hajimu Iida
  The 23rd International Conference on Mining Software Repositories (MSR 2026 Mining Challenge Track). [CORE A]

• Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage
  Suzuka Yoshimoto, Shun Fujita, Kosei Horikawa, Daniel Feitosa, Yutaro Kashiwa, Hajimu Iida
  The 23rd International Conference on Mining Software Repositories (MSR 2026 Mining Challenge Track). [CORE A]

Preprints

• Agentic Refactoring: An Empirical Study of AI Coding Agents
  Kosei Horikawa, Hao Li, Yutaro Kashiwa, Bram Adams, Hajimu Iida, Ahmed E. Hassan
  arXiv preprint arXiv:2511.04824, 2025.

Awards

• Best International Poster Award, IPSJ/SIGSE Software Engineering Symposium, 2025.