AI-Based Autonomous Code Generation and Optimization for Enhancing Software Reliability in Computer Systems
DOI:
https://doi.org/10.63282/3050-9416.IJAIBDCMS-V6I3P107Keywords:
Autonomous Code Generation, Software Reliability, Artificial Intelligence, Deep Learning, Program Optimization, Code Synthesis, Machine Learning, Software EngineeringAbstract
The growing complexity of software systems in the present day has provided impetus to the enigmatic automation of code generation, optimization, and quality assurance. The conventional software development practices assume manual software development, and optimization (which is heuristic) and this practice creates human error, inefficiency, and scalability issues in large-scale applications. Towards curbing these constraints, this research paper suggests a neural artificial intelligence framework combining deep learning and reinforcement learning to generate, analyze, and optimize computer code to achieve greater software availability and effectiveness. The model uses a code generating Transformer and a reinforcement learning optimizer, which runs in a closed feedback loop, which can be improved in an iterative manner using reliability-based reward signals. Benchmark databases like CodeNet, CodeXGLUE experiments were conducted in various programming languages. The designed model improved on the baseline AI systems and traditional optimization instruments by 37.4% in terms of code reliability, 29.8% decreased in execution errors, and 24.1% enhanced in running time performance. The self-adaptive feedback organization would guarantee the design of continuous improvement without a human being which shows the possibility of completely autonomous and reliability conscious software development. The article provides the basis of autonomous software engineering of the next generation, in which AI-based systems will be able not only to create effective code, which is both maintainable and efficient, but also actively improve the property of robustness, maintainability, and operational safety of sophisticated computational settings
References
1. Allamanis, M., Brockschmidt, M., & Khademi, M. (2017). Learning to represent programs with graphs. arXiv preprint arXiv:1711.00740.
2. Zhang, K., Wang, W., Zhang, H., Li, G., & Jin, Z. (2022, May). Learning to represent programs with heterogeneous graphs. In Proceedings of the 30th IEEE/ACM international conference on program comprehension (pp. 378-389).
3. Bui, N. D., Le, H., Wang, Y., Li, J., Gotmare, A. D., & Hoi, S. C. (2023). Codetf: One-stop transformer library for state-of-the-art code llm. arXiv preprint arXiv:2306.00029.
4. Wong, M. F., Guo, S., Hang, C. N., Ho, S. W., & Tan, C. W. (2023). Natural language generation and understanding of big code for AI-assisted programming: A review. Entropy, 25(6), 888.
5. Elnaggar, A., Ding, W., Jones, L., Gibbs, T., Feher, T., Angerer, C., ... & Rost, B. (2021). Codetrans: Towards cracking the language of silicon's code through self-supervised deep learning and high performance computing. arXiv preprint arXiv:2104.02443.
6. Allamanis, M., Barr, E. T., Devanbu, P., & Sutton, C. (2018). A survey of machine learning for big code and naturalness. ACM Computing Surveys (CSUR), 51(4), 1-37.
7. Sharma, T., Kechagia, M., Georgiou, S., Tiwari, R., Vats, I., Moazen, H., & Sarro, F. (2024). A survey on machine learning techniques applied to source code. Journal of Systems and Software, 209, 111934.
8. Generative AI Automation: Transforming Productivity, Efficiency, and Operational Excellence, solulab. online. https://www.solulab.com/generative-ai-automation/
9. Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., ... & Vinyals, O. (2022). Competition-level code generation with alphacode. Science, 378(6624), 1092-1097.
10. Zhu, J., & Shen, M. (2020, April). Research on Deep learning Based Code generation from natural language Description. In 2020 IEEE 5th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) (pp. 188-193). IEEE.
11. Soliman, A. S., Hadhoud, M. M., & Shaheen, S. I. (2022). MarianCG: a code generation transformer model inspired by machine translation. Journal of Engineering and Applied Science, 69(1), 104.
12. Beau, N., & Crabbé, B. (2022). The impact of lexical and grammatical processing on generating code from natural language. arXiv preprint arXiv:2202.13972.
13. Velaga, S. P. (2020). Ai-assisted code generation and optimization: Leveraging machine learning to enhance software development processes. International Journal of Innovations in Engineering Research and Technology, 7(09), 177-186.
14. Shim, S., Patil, P., Yadav, R. R., Shinde, A., & Devale, V. (2020, January). DeeperCoder: Code generation using machine learning. In 2020 10th Annual Computing and Communication Workshop and Conference (CCWC) (pp. 0194-0199). IEEE.
15. Odeh, A. (2024). Exploring AI innovations in automated software source code generation: Progress, hurdles, and future paths. Informatica, 48(8).
16. Sobania, D., Schweim, D., & Rothlauf, F. (2022). A comprehensive survey on program synthesis with evolutionary algorithms. IEEE Transactions on Evolutionary Computation, 27(1), 82-97.
17. Odeh, A., Odeh, N., & Mohammed, A. S. (2024). A comparative review of AI techniques for automated code generation in software development: advancements, challenges, and future directions. TEM Journal, 13(1), 726.
18. Allamanis, M., Barr, E. T., Bird, C., Devanbu, P., Marron, M., & Sutton, C. (2016). Mining semantic loop idioms from Big Code. In Technical Report.
19. Imam, A. T., Rousan, T., & Aljawarneh, S. (2014, April). An expert code generator using rule-based and frames knowledge representation techniques. In 2014 5th International Conference on Information and Communication Systems (ICICS) (pp. 1-6). IEEE.
20. Hu, K., Duan, Z., Wang, J., Gao, L., & Shang, L. (2019). Template-based AADL automatic code generation. Frontiers of Computer Science, 13(4), 698-714.
21. Terragni, V., Roop, P., & Blincoe, K. (2024). The future of software engineering in an AI-driven world. arXiv preprint arXiv:2406.07737.
22. Studying the Quality of Source Code Generated by Different AI Generative Engines: An Empirical Evaluation — (2024).
23. Optimization based machine learning algorithms for software reliability growth models — Shin, M., Jung, J., Lee, J., Ryu, I., Park, S. (2023). Journal of Advances in Military Studies. Applies ML/optimization methods to software reliability growth models.
