58 citations · 118 across the 5 of their papers we have counts for
3 papers · 1 filter
What Do AI Agents Actually Change? An Empirical Taxonomy of Mutation Patterns in Performance-Improving Pull Requests
Illia Dovhoshliubnyi, Nima Soroush, Ashkan Sami +1
AI coding agents are black boxes: we cannot inspect how they generate code, but we can inspect what they change. This distinction matters for search-based software engineering (SBS…
LLM-Guided Genetic Improvement: Envisioning Semantic Aware Automated Software Evolution
Karine Even-Mendoza, Alexander Brownlee, Alina Geiger +4
Genetic Improvement (GI) of software automatically creates alternative software versions that are improved according to certain properties of interests (e.g., running-time). Search…
Enhancing Genetic Improvement Mutations Using Large Language Models
Alexander E. I. Brownlee, James Callan, Karine Even-Mendoza +5
Large language models (LLMs) have been successfully applied to software engineering tasks, including program repair. However, their application in search-based techniques such as G…