Reproduce “Empirical Insights from AI-Powered Software Engineering in Practice” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tina Mersch, Jack Johns, Steffen Klepke, Hanya Elhashemy, Artur Signell, Robin Gröpler, Klaus Schmid
The authors examine delegation to generative AI across three cases, from suggestions to autonomous agents. Their spectrum describes levels of control, not a tested policy. In a two-week prototype study, AI aided conceptual design but struggled with backend work. Siemens respondents rated codebase understanding positively more often (73.3%) than refactoring suggestions (62.2%) or implementation (58.8%), survey feedback rather than performance measures.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.