Enhancing Genetic Improvement Mutations Using Large Language Models

TL;DR

This paper explores using large language models as mutation operators in genetic improvement to enhance search efficiency, showing increased patch success rates but less diversity compared to standard methods.

Contribution

It introduces LLMs as mutation operators in GI, expanding the Gin Java toolkit to leverage OpenAI's API for generating code edits.

Findings

Up to 75% more patches pass unit tests with LLM-based edits.

LLM-generated patches are less diverse than standard edits.

Standard GI found the best runtime improvement patches.

Abstract

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.