1 citations · 1 across the 5 of their papers we have counts for
6 papers · 1 filter
Is Self-Admitted Technical Debt Tested? An Empirical Study of Coverage, Co-change, and Impact
Suzuka Yoshimoto, Kosei Horikawa, Daniel Feitosa +2
When developers write a TODO or FIXME comment, they are explicitly admitting that the code is suboptimal: a built-in warning that this logic deserves extra scrutiny. Yet it is an o…
AgentLogs: A Dataset for Opening the Black Box of Cloud Agents on GitHub
Jonan Richards, Kosei Horikawa, Youmei Fan +2
Coding agents now complete development tasks in real software projects and submit the results as pull requests. A pull request shows the outcome of an agent's execution but not the…
What Are Developers Actually Discussing When Visual Regression Tests Fail?
Miku Watanabe, Kosei Horikawa, Brittany Reid +2
Visual Regression Tests (VRTs) are widely adopted as a mechanism for detecting unintended visual changes in user interfaces. By design, VRTs operate on rendered pixel output, and t…
Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage
Suzuka Yoshimoto, Shun Fujita, Kosei Horikawa +3
Agent-based coding tools have transformed software development practices. Unlike prompt-based approaches that require developers to manually integrate generated code, these agent-b…
Do AI Agents Really Improve Code Readability?
Kyogo Horikawa, Kosei Horikawa, Yutaro Kashiwa +2
Code readability is fundamental to software quality and maintainability. Poor readability extends development time, increases bug-inducing risks, and contributes to technical debt.…
Agentic Refactoring: An Empirical Study of AI Coding Agents
Kosei Horikawa, Hao Li, Yutaro Kashiwa +3
Agentic coding tools, such as OpenAI Codex, Claude Code, and Cursor, are changing how software is developed. These AI-powered systems function as autonomous teammates capable of pl…