Keywords:-
Article Content:-
Abstract
Automated code review aims to reduce manual effort, catch defects early, and improve code quality by using machine learning and Natural Language Processing (NLP) to analyze source changes, generate review comments, and prioritize reviewer attention. This paper surveys prior work and presents a practical methodology combining transformer-based code models (e.g., CodeBERT/CodeT5-style encoders), structural program representations (ASTs/graphs), and comment-generation components to build an automated code review assistant. We describe dataset collection from open-source pull requests, preprocessing, model design, evaluation metrics, and an implementation plan. Finally, we discuss expected benefits, limitations, and directions for future work. (arXiv)
References:-
References
R. Tufano, L. Pascarella, M. Tufano, D. Poshyvanyk, and G. Bavota, “Towards Automating Code Review Activities,” Proc. 43rd Int. Conf. Software Engineering (ICSE), 2021, pp. 163–174.
Y. Yin, Y. Zhao, Y. Sun, and C. Chen, “Automatic Code Review by Learning the Structure Information of Code Graph,” Sensors, vol. 23, no. 5, art. 2551, Feb. 2023.
G. Tucudean, C. Pop, and D. Petrescu, “Natural Language Processing with Transformers: A Review,” MDPI Applied Sciences, 2024.
A. Frömmgen, M. Beller, and A. Zeller, “Resolving Code Review Comments with Machine Learning,” Google Research Technical Report, 2024.
G. Zhao, D. A. da Costa, and Y. Zou, “Improving the Pull Requests Review Process Using Learning-to-Rank Algorithms,” Empirical Software Engineering, vol. 24, no. 3, pp. 1759–1787, 2019.
X. Chen, Y. Liu, and M. Zhao, “Automatic Code Review by Learning Code Semantics and Reviewer Behaviors,” IEEE Trans. Software Engineering, vol. 46, no. 8, pp. 850–862, 2020.
S. Nate, O. Patil, S. Medar, and J. Deshmukh, “A Survey on Transformer-based Models in Code Summarization,” Int. Res. J. Adv. Eng. Hub (IRJAEH), vol. 3, no. 3, pp. 740–745, Mar. 2025.
“Promises and Perils of Using Transformer-based Models for Software Engineering Research,” Empirical Software Engineering, Elsevier, 2024.
R. Tufano, M. Tufano, D. Poshyvanyk, and G. Bavota, “Impact Studies on LLM-Generated Review Comments and Reviewer Interactions,” arXiv Preprint arXiv:2405.10234, 2024.
Y. Yin, Y. Zhao, Y. Sun, and C. Chen, “Automatic Code Review by Learning the Structure of Code Graph,” MDPI Sensors, 2023.
U. Cihan, V. Haratian, A. İcöz, M. K. Gül, Ö. Devran, E. F. Bayendur, B. M. Uçar, and E. Tüzün, “Automated Code Review In Practice,” Bilkent University Technical Report, 2024. ResearchGate
Y. Kartal, “Automating Modern Code Review Processes with Transformer-based Models,” Computers & Security, vol. ?, no. ?, pp. ?, 2024. ScienceDirect
H. Y. Lin, P. Thongtanunam, C. Treude, M. W. Godfrey, C. Liu, and W. Charoenwet, “Leveraging Reviewer Experience in Code Review Comment Generation,” arXiv Preprint arXiv:2409.10959, 2024. arXiv+1
Z. Rasheed, M. A. Sami, M. Waseem, K.-K. Kemell, X. Wang, A. Nguyen, K. Systä, and P. Abrahamsson, “AI-Powered Code Review with Large Language Models: Early Results,” arXiv Preprint arXiv:2404.18496, 2024. arXiv
T. Sun, J. Xu, Y. Li, Z. Yan, G. Zhang, L. Geng, Z. Wang, Y. Chen, Q. Lin, and W. Duan, “BitsAI-CR: Automated Code Review via Large Language Models in Practice,” arXiv Preprint arXiv:2501.15134, 2025.