Artificial Intelligence in Code Optimization and Refactoring
DOI:
https://doi.org/10.32628/CSEIT25112463Keywords:
Artificial Intelligence, AI, Code Optimization, Refactoring, CodeT5, Codex, Neural Compressor, Refactoring Miner, Automated Test, Self-Adaptive Code, DevOps, CI/CD, Software EngineeringAbstract
AI has become useful in software development to help improve on code optimization/ refactoring exercises thus boosting on productivity, performance and sustainable maintainability. AI tools including CodeT5, Codex, Intel’s Neural Compressor, and Refactoring Miner help the developers to analyze the code, minimize it and advance refactoring engagements. This paper investigates the deployment of AI in code optimization and their performances in optimizing common codes used across industries on real-world case, highlighting the impacts of AI in enhancing system performance, code read abilities, and Reducing on the over burdensome and ailing technical debt stock. It also explores new frontiers in AI for software engineering; testing & quality assurance; self-adaptive code; program synthesis, which may completely alter the development cycle and coding methods during the subsequent decade. This paper also responds to other essential concerns: data accessibility, the generalization of an AI model, interpretability and expandability, which affects the applicability and adoption of AI solutions. This paper aims to discuss how such advancements and challenges show how AI is valuable in identifying code improvement possibilities and supports the creation of efficient methods for improving software quality on an ongoing basis.
Downloads
References
R. K. S. K. L. a. P. N. Panigrahi, "A systematic approach for software refactoring based on class and method level for AI application.," International Journal of Powertrains, , vol. 10, no. 2, pp. pp.143-174., 2021.
K. a. G. D. Wang, Applying AI techniques to program optimization for parallel computers., 1987.
T. G. J. a. R. A. Jiang, Supervised machine learning: a brief primer. Behavior therapy, 51(5), pp.675-687., 2020.
M. Q. J. R. A. A. H. Y. K. E. Y. H. A. a. A.-F. A. Usama, Unsupervised machine learning for networking: Techniques, applications and research challenges., IEEE access, 7, pp.65579-65615., 2019.
A. O. M. Z. N. M. G. a. A. S. Almogahed, Revisiting scenarios of using refactoring techniques to improve software systems quality., IEEE Access, 11, pp.28800-28819., 2022.
S. Javaid, "Crowdsourced Data Collection Benefits & Best Practices," 24 oct 2024. [Online]. Available: https://research.aimultiple.com/crowdsourced-data/.
T. Hospedales, "Meta-Learning in Neural Networks," Samsung AI Center - Cambridge, 2 Sep 2021. [Online]. Available: chat.openai.com/?model=text-davinci-002-render-sha.
V. C. Vikas Hassija, "Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence," springer links, 24 August 2023. [Online]. Available: https://link.springer.com/article/10.1007/s12559-023-10179-8.
S. Kate, "Parallel and Distributed Computing," Medium, 25 April 2023. [Online]. Available: https://medium.com/@sumedhkate/parallel-and-distributed-computing-9ee800c9aa8e.
Y. W. W. J. S. a. H. S. Wang, Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation., arXiv preprint arXiv:2109.00859., 2021.
Yue, "CodeT5: The Code-aware Encoder-Decoder based Pre-trained Programming Language Models," The 360 Blog, 3 sep 2021. [Online]. Available: https://www.salesforce.com/blog/codet5/.
M. &. S.-D. A. &. P. I. &. S. S. Sandalski, " Development of a Refactoring Learning Environment. 11.," 2011.
C. Morrison, "Assessing AI system performance: thinking beyond models to deployment contexts," Microsoft Research Blog, 26 September 2022. [Online]. Available: https://www.microsoft.com/en-us/research/blog/assessing-ai-system-performance-thinking-beyond-models-to-deployment-contexts/.
B. T, "How did I leverage AI and Generative AI in Agile Deployments and in building BizDevOps & DevSecOps pipeline in IT engagements," Linked In, 11 August 2024. [Online]. Available: https://www.linkedin.com/pulse/how-did-i-leverage-ai-generative-agile-deployments-building-balaji-t-iuipc.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Computer Science, Engineering and Information Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.