Evolutionary Software Development Methodologies Integrating Machine Learning-Driven Code Generation and Automated Bug Fixing Mechanisms
Keywords:
Evolutionary software development, machine learning code generation, automated bug fixing, AI in software engineering, automated program repairAbstract
The rapid evolution of software development necessitates automated mechanisms to enhance efficiency, reduce costs, and improve software quality. This paper explores evolutionary software development methodologies that integrate machine learning (ML)-driven code generation and automated bug-fixing techniques. We analyze state-of-the-art advancements in ML-based program synthesis, deep learning-based debugging, and automated program repair (APR). The study discusses key methodologies, challenges, and future research directions, highlighting the impact of AI-powered code generation on software engineering.
References
Arcuri, A., & Yao, X. "Co-evolutionary automatic programming for software development." Information Sciences, 2014.
Bajaj, Y., & Samal, M. K. "Accelerating software quality: Unleashing the power of Generative AI for Automated Test-case generation and bug identification." International Journal of Research in Applied Science and Engineering, 2023.
Cao, H., et al. "A survey on automatic bug fixing." IEEE Systems and Software, 2020.
Tufano, M., et al. "An empirical study on learning bug-fixing patches in the wild via neural machine translation." Software Engineering, 2019.
Wan, Z., et al. "How does machine learning change software development practices?" IEEE Transactions on Software Engineering, 2019.
Weimer, W., et al. "Automatic program repair with evolutionary computation." Communications of the ACM, 2010.
Xia, C. S., et al. "Automated program repair in the era of large pre-trained language models." IEEE Software Engineering Conference, 2023.
Zheng, Y., et al. "Wuji: Automatic online combat game testing using evolutionary deep reinforcement learning." IEEE Automated Software Engineering, 2019.
Lee, D. G., & Seo, Y. S. "Improving bug report triage performance using artificial intelligence-based document generation model." Human-centric Computing and Information Sciences, 2020.
Yuan, Y., & Banzhaf, W. "A hybrid evolutionary system for automatic software repair." Genetic and Evolutionary Computing Conference, 2019.
Sobania, D., et al. "An analysis of the automatic bug fixing performance of ChatGPT." Automated Program Repair, 2023.
Jahanshahi, H., et al. "Wayback Machine: Evolutionary behavior of bug reports and triage." Journal of Systems and Software, 2022.
Ojdanic, M., et al. "Mutation testing in evolving systems." Software Engineering, 2023.
Wan, C., et al. "Automated testing of software that uses machine learning APIs." Software Engineering, 2022.
Le, T. H. M., et al. "Deep learning for source code modeling and generation." ACM Computing Surveys, 2020.
Yang, Y., et al. "A comprehensive empirical study on bug characteristics of deep learning frameworks." Information and Software Technology, 2022.
Dilhara, M., et al. "Understanding software-2.0: A study of machine learning library usage and evolution." ACM Transactions on Software Engineering, 2021.
Mantere, T., & Alander, J. T. "Evolutionary software engineering: A review." Applied Soft Computing, 2005.
