Abstract Ever since the first large language models (LLMs) have become available, both academics and practitioners have used them to aid software engineering tasks. However, little research as yet has been done in combining search-based software engineering (SBSE) and LLMs. In this paper, we evaluate the use of LLMs as mutation operators for genetic improvement (GI), an SBSE approach, to improve the GI search process. In a preliminary work, we explored the feasibility of combining the Gin Java GI toolkit with OpenAI LLMs in order to generate an edit for the tool. Here we extend this investigation involving three LLMs and three types of prompt, and five real-world software projects. We sample the edits at random, as well as using local search. We also conducted a qualitative analysis to understand why LLM-generated code edits break as part of our evaluation. Our results show that, compared with conventional statement GI edits, LLMs produce fewer unique edits, but these compile and pass tests more often, with the model finding test-passing edits 77% of the time. The and LLMs are roughly equal in finding the best run-time improvements. Simpler prompts are more successful than those providing more context and examples. The qualitative analysis reveals a wide variety of areas where LLMs typically fail to produce valid edits commonly including inconsistent formatting, generating non-Java syntax, or refusing to provide a solution.

Automated program repair techniques aim to aid software developers with the challenging task of fixing bugs. In heuristic-based program repair, a search space of mutated program variants is explored to find potential patches for bugs. Most commonly, every selection of a mutation operator during search is performed uniformly at random, which can generate many buggy, even uncompilable programs. Our goal is to reduce the generation of variants that do not compile or break intended functionality which waste considerable resources. In this paper, we investigate the feasibility of a reinforcement learning-based approach for the selection of mutation operators in heuristic-based program repair. Our proposed approach is programming language, granularity-level, and search strategy agnostic and allows for easy augmentation into existing heuristic-based repair tools. We conducted an extensive empirical evaluation of four operator selection techniques, two reward types, two credit assignment strategies, two integration methods, and three sets of mutation operators using 30,080 independent repair attempts. We evaluated our approach on 353 real-world bugs from the Defects4J benchmark. The reinforcement learning-based mutation operator selection results in a higher number of test-passing variants, but does not exhibit a noticeable improvement in the number of bugs patched in comparison with the baseline, uniform random selection. While reinforcement learning has been previously shown to be successful in improving the search of evolutionary algorithms, often used in heuristic-based program repair, it has yet to demonstrate such improvements when applied to this area of research.

Background: Quantum computing is a rapidly growing new programming paradigm that brings significant changes to the design and implementation of algorithms. Understanding quantum algorithms requires knowledge of physics and mathematics, which can be challenging for software developers. Aims: In this work, we provide a first analysis of how LLMs can support developers’ understanding of quantum code. Method: We empirically analyse and compare the quality of explanations provided by three widely adopted LLMs (Gpt3.5, Llama2, and Tinyllama) using two different human-written prompt styles for seven state-of-the-art quantum algorithms. We also analyse how consistent LLM explanations are over multiple rounds and how LLMs can improve existing descriptions of quantum algorithms. Results: Llama2 provides the highest quality explanations from scratch, while Gpt3.5 emerged as the LLM best suited to improve existing explanations. In addition, we show that adding a small amount of context to the prompt significantly improves the quality of explanations. Finally, we observe how explanations are qualitatively and syntactically consistent over multiple rounds. Conclusions: This work highlights promising results, and opens challenges for future research in the field of LLMs for quantum code explanation. Future work includes refining the methods through prompt optimisation and parsing of quantum code explanations, as well as carrying out a systematic assessment of the quality of explanations.

With our reliance on software continuously increasing, it is of utmost importance that it be reliable. However, complete prevention of bugs in live systems is unfortunately an impossible task due to time constraints, incomplete testing, and developers not having knowledge of the full stack. As a result, mitigating risks for systems in production through hot patching and hot fixing has become an integral part of software development. In this paper, we first give an overview of the terminology used in the literature for research on this topic. Subsequently, we build upon these findings and present our vision for an automated framework for predicting and mitigating critical software issues at runtime. Our framework combines hot patching and hot fixing research from multiple fields, in particular: software defect and vulnerability prediction, automated test generation and repair, as well as runtime patching. We hope that our vision inspires research collaboration between the different communities.