Exploring the Feasibility of Retrieval-Augmented Generation for Software Defect Analysis: An Empirical Study
DOI:
https://doi.org/10.5753/reic.2026.6811Keywords:
Data Mining, Software Defect Repositories, Large Language Models, Software TestingAbstract
A defect database is a structured collection of information about software bugs, errors, and their resolutions throughout the development lifecycle. These databases have valuable information for improving software quality, but their growing volume and complexity make manual analysis inefficient and error-prone. This paper presents an empirical study using real-world data investigating the feasibility of Retrieval-Augmented Generation (RAG) to support interactive exploration of software defect repositories. The study is structured with reference to selected phases of the CRISP-DM framework, which was used as an organizational guideline. Using a real-world software defect database as the empirical basis, the approach automates insight extraction from defect repositories, aiming to improve decision-making in quality assurance and software development by enabling scalable and intelligent exploration of software failures.
Downloads
Referências
Al-Batlaa, A., Abdullah-Al-Wadud, M., and Anwar, M. (2019). A method to suggest solutions for software bugs. In 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR), pages 169–172. IEEE. DOI: 10.1109/ICIEV.2019.8858514.
Badgett, T., Myers, G. J., et al. (2012). The Art of Software Testing. Wiley-Blackwell.
Edström, J. (2024). Rag-based data extraction: Mining information from second-life battery documents. Available at: [link].
Getachew, M., Beshah, B., Mulugeta, A., and Kitaw, D. (2024). Application of artificial intelligence to enhance manufacturing quality and zero-defect using crisp-dm framework. International Journal of Production Research, pages 1–25. DOI: 10.1080/00207543.2024.2407919.
Jamil, M. A., Arif, M., Abubakar, N. S. A., and Ahmad, A. (2016). Software testing techniques: A literature review. In 2016 6th international conference on information and communication technology for the Muslim world (ICT4M), pages 177–182. IEEE. DOI: 10.1109/ICT4M.2016.045.
Last, M., Friedman, M., and Kandel, A. (2003). The data mining approach to automated software testing. In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, pages 388–396. DOI: 10.1145/956750.956795.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–9474. Available at: [link].
Milojević, D., Macuzic, I., Djordjevic, A., Savković, M., and Djapan, M. (2023). Comparative analysis of software tools for agile project management. Available at: [link].
PÁDUA, A. and SOUSA, F. (2018). Metodologia crisp-dm: potencialidades na descoberta do conhecimento em dados educacionais. In XVI Congresso Internacional de Tecnologia na Educação. Educação e Tecnologia em Tempos de Mudança. Available at: [link].
Sousa, É. M., Rodrigues, A., Teixeira, N., Santos, I. S., Francisco, M. S., Andrade, R. M. d. C., and Vasconcelos, D. R. (2022). From past to future: An experience using data mining to guide tests. In Proceedings of the XXI Brazilian Symposium on Software Quality, pages 1–10. DOI: 10.1145/3571473.3571493.
Downloads
Published
Como Citar
Issue
Section
Licença
Copyright (c) 2026 Pedro Lucas de Lavor Farias, Levi Almeida da Silva, Pedro Almir M. Oliveira; Ismayle de Sousa Santos
Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
