16 papers
Loop Engineering: Building Blocks, Adoption, and Impact
Jai Lal Lulla, Vahram Nersesyan, Seyedmoein Mohsenimofidi +2
Over the past months, the way developers direct agentic AI coding tools has moved up several levels of abstraction, from phrasing prompts to engineering context to configuring the…
An Exploratory Study of Agent Plans for Agentic AI Coding Tools in Open-Source Software
Muhammad Auwal Abubakar, Seyedmoein Mohsenimofidi, Jai Lal Lulla +4
Repository-level configuration artifacts allow developers to provide guidance for agentic AI coding tools, such as Claude Code, Gemini, etc. Although prior research has examined re…
Motivations and Barriers to Communicating Software Engineering Research: Insights from Early Career Researchers
Shalini Chakraborty, Marvin Wyrich, Sven Apel +1
Science communication is increasingly becoming a part of modern research careers, involving researchers to disseminate knowledge, engage broader communities, and increase the socie…
From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained
Haoyu Gao, Jai Lal Lulla, Hong Yi Lin +3
AI coding agents increasingly rely on skills: structured context bundles, typically a SKILLmd file with a YAML header and Markdown body, loaded on demand for domain knowledge, w…
Harness Engineering for Agentic AI Coding Tools: An Exploratory Study
Matthias Galster, Seyedmoein Mohsenimofidi, Jai Lal Lulla +3
Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSO…
"An Endless Stream of AI Slop": How Developers Discuss the Burden of AI-Assisted Software Development
Sebastian Baltes, Marc Cheong, Christoph Treude
"AI slop", that is, low-quality AI-generated content, is increasingly affecting software development, from generated code and pull requests to documentation and bug reports. Howeve…