AI in Software Engineering: Automating Debugging and Code Optimization
Keywords:
Artificial intelligence (AI), Bug detection and fixing, Code optimization, Debugging, Generative AI, Role of machine learningAbstract
Artificial Intelligence (AI) is revolutionizing software development by automating key processes such as debugging and code optimization, enhancing both efficiency and accuracy. Traditional debugging methods require manual inspection, which is time-consuming and prone to human error. In contrast, AI-driven debugging tools leverage machine learning to detect, predict, and resolve errors with minimal intervention, significantly reducing development time and improving software reliability. Similarly, AI-powered code optimization techniques analyse code structures, eliminate redundancies, and recommend performance improvements, ensuring resource-efficient applications.
This research explores the impact of AI in debugging and code optimization, highlighting various AI-driven techniques, tools, and frameworks that enhance software development. Tools like Deep Code and IntelliCode provide intelligent recommendations, automating error detection and performance enhancements. Machine learning models assist in identifying coding patterns, predicting potential issues, and even automating bug fixes through deep learning and reinforcement learning approaches. AI-driven optimization techniques such as code refactoring and performance tuning further improve software efficiency.
Despite these advancements, challenges remain, including AI model biases, false positives in bug detection, and integration complexities. This study examines these limitations and proposes potential solutions. By analysing AI’s role in software engineering, this research provides insights into how AI can streamline development workflows, improve software quality, and shape the future of programming through automation and intelligent code analysis.
References
G. Fan, X. Xie, X. Zheng, Y. Liang, and P. Di, “Static code analysis in the AI era: An in-depth exploration of the concept, function, and potential of intelligent code analysis agents,” arXiv preprint, arXiv:2310.08837, Oct. 13, 2023. [Online] Available: https://arxiv.org/abs/2310.08837.
K. Levin, N. van Kempen, E. D. Berger, and S. N. Freund, “Chatdbg: An AI-powered debugging assistant,” arXiv preprint, arXiv:2403.16354, Mar. 25, 2024. [Online] Available: https://arxiv.org/abs/2403.16354.
M. R. Rosas, M. T. Sanchez, and R. Eigenmann, “Should AI optimize your code? A comparative study of current large language models versus classical optimizing compilers,” arXiv preprint, arXiv:2406.12146, Jun. 17, 2024. [Online] Available: https://arxiv.org/abs/2406.12146.
C. Lee, C. S. Xia, L. Yang, J. T. Huang, Z. Zhu, L. Zhang, and M. R. Lyu, “A unified debugging approach via LLM-based multi-agent synergy,” arXiv preprint, arXiv:2404.17153, Apr. 26, 2024. [Online] Available: https://arxiv.org/abs/2404.17153.
V. A. Hall, Coding with ChatGPT and Other LLMs: Navigate LLMs for Effective Coding, Debugging, and AI-Driven Development. Packt Publishing, 2024. [Online] Available: https://ieeexplore.ieee.org/document/10803972.
U. K. Durrani, M. Akpinar, M. F. Adak, A. T. Kabakus, M. M. Ozturk, and M. Saleh, “A decade of progress: A systematic literature review on the integration of AI in software engineering phases and activities (2013–2023),” IEEE Access, vol. 12, pp. 171185-171204, Nov. 1, 2024. [Online] Available: https://ieeexplore.ieee.org/document/10740293.
U. Garg, “Exploring the use of artificial intelligence for software testing and debugging,” Int. J. Electr. Eng. Technol. (IJEET), vol. 11, no. 1, pp. 94–102, 2020. [Online] Available: https://iaeme.com/Home/article_id/IJEET_11_01_009.
G. Shekhar, The Impact of AI and Automation on Software Development: A Deep Dive, 2024. [Online] Available: https://ieeechicago.org/the-impact-of-ai-and-automation-on-software-development-a-deep-dive/.
M. S. Bajwa, A. P. Agarwal, and N. Gupta, “Code optimization as a tool for testing software,” in Proc. 3rd Int. Conf. Comput. Sustain. Global Develop. (INDIACom), Mar. 16–18, 2016, pp. 961–967. [Online] Available: https://ieeexplore.ieee.org/document/7724405.
C. Bull and A. Kharrufa, “Generative artificial intelligence assistants in software development education: A vision for integrating generative artificial intelligence into educational practice, not instinctively defending against it,” IEEE Softw., vol. 41, no. 2, pp. 52–59, Aug. 8, 2023. [Online] Available: https://ieeexplore.ieee.org/abstract/document/10213396.
