Book Chapter

Enhancing Genetic Improvement Mutations Using Large Language Models



Brownlee A, Callan J, Even-Mendoza K, Geiger A, Hanna C, Petke J, Sarro F & Sobania D (2023) Enhancing Genetic Improvement Mutations Using Large Language Models. In: Arcaini P, Yue T & Fredericks EM (eds.) Search-Based Software Engineering: 15th International Symposium, SSBSE 2023, San Francisco, CA, USA, December 8, 2023, Proceedings. Lecture Notes in Computer Science. Cham, Switzerland: Springer.

Large language models (LLMs) have been successfully applied to software engineering tasks, including program repair. However, their application in search-based techniques such as Genetic Improvement (GI) is still largely unexplored. In this paper, we evaluate the use of LLMs as mutation operators for GI to improve the search process. We expand the Gin Java GI toolkit to call OpenAI's API to generate edits for the JCodec tool. We randomly sample the space of edits using 5 different edit types. We find that the number of patches passing unit tests is up to 75% higher with LLM-based edits than with standard Insert edits. Further, we observe that the patches found with LLMs are generally less diverse compared to standard edits. We ran GI with local search to find runtime improvements. Although many improving patches are found by LLM-enhanced GI, the best improving patch was found by standard GI.

StatusIn Press
FundersEngineering and Physical Sciences Research Council and European Commission (Horizon 2020)
Title of seriesLecture Notes in Computer Science
Publication date online31/12/2023
Publisher URL
Place of publicationCham, Switzerland
ISSN of series0302-9743

People (1)


Dr Sandy Brownlee

Dr Sandy Brownlee

Senior Lecturer in Computing Science, Computing Science and Mathematics - Division