5 papers
Do Coding Agents Follow AGENTS.md? The Effect of Policy Wording on Instruction Compliance
Rikuto Tsuchida, Youmei Fan, Kazumasa Shimari +2
Coding agents do not always follow the policies in an Agent Context File (ACF). We inserted one policy, in four styles, into the ACFs of 86 benchmark tasks across four harness-mode…
Predicting Struggling Students in CS1 Programming Using Keystroke-Level Editing Features
Yasuyo Kofune, Kazumasa Shimari, Kenichi Matsumoto
This paper investigates the feasibility of early detection of struggling students during CS1 programming exercises using keystroke-level logs. Some students fail to reach a correct…
How Do Developers Use Migration Guides? A Case Study of Log4j
Takahiro Monno, Kazumasa Shimari, Tetsuya Kanda +2
Migration guides are a form of software documentation that helps developers address breaking changes introduced in library version updates. Prior studies have examined documents su…
How AI Coding Agents Communicate: A Study of Pull Request Description Characteristics and Human Review Responses
Kan Watanabe, Rikuto Tsuchida, Takahiro Monno +5
The rapid adoption of large language models has led to the emergence of AI coding agents that autonomously create pull requests on GitHub. However, how these agents differ in their…
Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests
Haruhiko Yoshioka, Takahiro Monno, Haruka Tokumasu +4
The automatic generation of pull requests (PRs) using AI agents has become increasingly common. Although AI-generated PRs are fast and easy to create, their merge rates have been r…