- author = "Karine Even-Mendoza and Alexander E. I. Brownlee and Alina Geiger and Carol Hanna and Justyna Petke and Federica Sarro and Dominik Sobania",
- title = "{LLM}-Guided Genetic Improvement: Envisioning Semantic Aware Automated Software Evolution",
- booktitle = "ASE 2025",
- year = "2025",
- editor = "Shin Yoo",
- address = "Seoul, South Korea",
- month = "16--20 " # nov,
- keywords = "genetic algorithms, genetic programming, genetic improvement, PatchCat, Large language models, AI, GIN, NLP, JUnit4, JCodec, Null Noop patch",
-
URL = "
https://kclpure.kcl.ac.uk/portal/en/publications/llm-guided-genetic-improvement-envisioning-semantic-aware-automat/",
-
URL = "https://arxiv.org/abs/2508.18089",
- size = "5 pages",
-
abstract = "... is instead a strength of GI.
As such, we propose the investigation of a new research line on AI-powered GI aimed at incorporating semantic aware search. We take a first step at it by augmenting GI with the use of automated clustering of LLM edits.
We provide initial empirical evidence that our proposal, dubbed PatchCat, allows us to automatically and effectively categorize LLM-suggested patches. PatchCat identified 18 different types of software patches and categorized newly suggested patches with high accuracy. It also enabled detecting NoOp edits in advance and, prospectively, to skip test suite execution to save resources in many cases. These results, coupled with the fact that PatchCat works with small, local LLMs, are a promising step toward interpretable, efficient, and green GI.
We outline a rich agenda of future work and call for the community to join our vision of building a principled understanding of LLM-driven mutations, guiding the GI search process with semantic signals.",
-
notes = "https://conf.researchr.org/program/ase-2025/program-ase-2025
See \cite{even2025llm}
PatchCat = Deep ANN based software source code patch categorisation.
'patch edit type' 'description of a patch'",
