Autonomous Code Review and Refactoring Suggestions Using AI-Augmented Software Engineering Agents

Nomura Ishikane Ichikawa

Autonomous Code Review and Refactoring Suggestions Using AI-Augmented Software Engineering Agents

Authors

Nomura Ishikane Ichikawa

AI-Augmented Software Engineer , United States

Keywords:

Autonomous Code Review, AI Agents, Software Refactoring, LLMs, Software Engineering, Developer Productivity

Synopsis

The increasing complexity of modern software systems necessitates intelligent tools for code maintenance and quality assurance. This paper explores the integration of AI-augmented software engineering agents for autonomous code review and refactoring. Drawing on recent advances in machine learning, multi-agent systems, and large language models (LLMs), we present the evolution, methodologies, and impact of these intelligent agents. A detailed literature review and a comparative analysis of current systems are included, highlighting trends, limitations, and future directions.

References

(1) Tufano, M., Watson, C., Bavota, G., Poshyvanyk, D.: An empirical study on learning bug-fixing patches in the wild via neural machine translation. Empir. Softw. Eng. 25(3), 2183–2224 (2020)

(2) Gummadi, V. P. K. (2019). Microservices architecture with APIs: Design, implementation, and MuleSoft integration. Journal of Electrical Systems, 15(4), 130–134. https://doi.org/10.52783/jes.9328

(3) Allamanis, M., Peng, H., Sutton, C.: A convolutional attention network for extreme summarization of source code. In: ICML 2016

(4) Ray, B., Posnett, D., Filkov, V., Devanbu, P.: A large-scale study of programming languages and code quality in GitHub. Commun. ACM 60(10), 91–100 (2017)

(5) Tsantalis, N., Mansouri, M., Mazinanian, D.: Accurate and efficient refactoring detection in commit history. In: ICSE 2018

(6) Rolim, R., Dyer, R., Lopes, C.V.: Learning meaningful code changes via neural machine translation. In: MSR 2017

(7) Sadowski, C., Van Gogh, J., Jaspan, C., Söderberg, E., Winter, C.: Tricorder: Building a program analysis ecosystem. In: ICSE 2015

(8) Chen, Z., Zhou, Y., Wang, J.: Towards code summarization with structural and semantic guidance. In: AAAI 2021

(9) Gummadi, V. P. K. (2020). API design and implementation: RAML and OpenAPI specification. Journal of Electrical Systems, 16(4). https://doi.org/10.52783/jes.9329

(10) Veeramachaneni, V.: AI-Augmented Software Development with Machine Learning. J. Comput. Anal. (2023)

(11) Pearce, H., Ahmad, M.Z., Tan, J., Dolan-Gavitt, B., Karri, R.: Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions. In: IEEE Symposium on Security and Privacy, pp. 1–18. IEEE (2022)

(12) Zhang, X., Yin, Y., Lin, C., Zhang, Y., Wang, Y.: On the Security and Quality of AI-generated Code: An Empirical Study. In: Proceedings of the 45th International Conference on Software Engineering (ICSE), pp. 251–263. IEEE/ACM (2023)

(13) Wang, Y., Shen, Y., Jin, X., Cui, Y., Wang, C., Zhang, H.: An Empirical Study of Developers’ Trust in AI-Powered Code Completion Tools. In: Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), pp. 1–12. ACM (2023)