Aidan Murphy

This paper introduces a novel mechanism, Feature Encapsulation by Stages (FES), to encapsulate and transfer features as knowledge in a staged manner within the evolutionary process. Encapsulation happens via input space expansion in one or more stages by adding the best-of-run individual as an additional input. This input space expansion is managed by augmenting the grammar. We study the feasibility of dynamically modifying the grammar and reinitialising the population to make way for new individuals which quickly evolve to a better fitness level. Five different approaches to stage management are examined. In addition, three different selection processes, namely, Tournament, Lexicase and Lexi², are used to investigate which is best suited to use with our encapsulation procedure. We benchmark our procedure on two problem domains, Boolean and Classification, and demonstrate these staging strategies lead to significantly better results. Statistical tests show our FES outperforms the standard baseline in all Boolean problems, with a 4-stage version performing best, obtaining significant differences in all Boolean problems.

Repairing bugs can be a daunting task for even a human experienced in debugging, so naturally, attempting to automatically repair programs with a computer system is quite challenging. The existing methods of automated program repair leave a lot of room for improvement. Fault localization, which aims to find lines of code that are potentially buggy, minimises the search space of an automated program repair system. Recent work has shown improvement in these fault localization methods, with the use of Large Language Models. Here, we propose a system where a LLM-based fault localization tool, which we call SemiAutoFL, is used within a fully automatic program repair program, ARJA-e. We show that utilising LLM-based fault localization with ARJA-e can significantly improve its performance on real world bugs. ARJA-e with SemiAutoFL can repair 10 bugs that ARJA-e was previously unable to so do. This finding adds to our understanding of how to improve fault localization and automated program repair, highlighting the potential for more efficient and accurate fault localisation methods being applied to automated program repair.

Grammatical Evolution is a Genetic Programming variant which evolves problems in any arbitrary language that is BNF compliant. Since its inception, Grammatical Evolution has been used to solve real-world problems in different domains such as bio-informatics, architecture design, financial modelling, music, software testing, game artificial intelligence and parallel programming. Multi-output problems deal with predicting numerous output variables simultaneously, a notoriously difficult problem. We present a Multi-Genome Grammatical Evolution better suited for tackling multi-output problems, specifically digital circuits. The Multi-Genome consists of multiple genomes, each evolving a solution to a single unique output variable. Each genome is mapped to create its executable object. The mapping mechanism, genetic, selection, and replacement operators have been adapted to make them well-suited for the Multi-Genome representation and the implementation of a new wrapping operator. Additionally, custom grammar syntax rules and a cyclic dependency-checking algorithm have been presented to facilitate the evolution of inter-output dependencies which may exist in multi-output problems. Multi-Genome Grammatical Evolution is tested on combinational digital circuit benchmark problems. Results show Multi-Genome Grammatical Evolution performs significantly better than standard Grammatical Evolution on these benchmark problems.