AI-Powered Intelligent Code Review and Pull Request Analysis System
Abstract
Modern code review is essential for defect prevention, maintainability, knowledge transfer, and collaborative software development, but manual review is frequently delayed by reviewer workload and inconsistent review depth. This paper presents ReviewPilot, a web-based prototype that integrates repository import, pull request analysis, static checks, large-language-model-assisted review, configurable review rules, issue summarisation, and a composite Code Health Score within a unified dashboard. The proposed workflow ingests repository and pull request metadata, validates and parses changed files, applies deterministic rules and conventional static analysis, and then invokes an AI review layer to generate context-sensitive observations. The results are organised by severity, file, and review category before being displayed through repository, pull request, rules, review-history, and dashboard interfaces. Functional interface testing confirms that the principal modules and navigation flow operate as intended in the simulated environment. However, the present work is a proof-of-concept system demonstration rather than a comparative evaluation of defect-detection accuracy, review usefulness, latency, security, or developer productivity. Accordingly, the paper defines an evaluation framework for future studies using labelled code changes, expert reviewer judgements, precision, recall, false-positive rate, response time, and user-centred measures. ReviewPilot therefore demonstrates a technically coherent architecture for AI-assisted review while recognising that human oversight, reproducible benchmarking, privacy controls, and hallucination mitigation remain necessary before production deployment.
References
A. Bacchelli, C. Bird, (2013). Expectations, outcomes, and challenges of modern code review. In 2013 35th international conference on software engineering (ICSE), IEEE, San Francisco, CA, USA. https://doi.org/10.1109/ICSE.2013.6606617
S. McIntosh, Y. Kamei, B. Adams, A.E. Hassan, (2014). The impact of code review coverage and code review participation on software quality: A case study of the Qt, VTK, and ITK projects, in Proc. 11th Working Conf. Mining Software Repositories (MSR), 192–201. https://doi.org/10.1145/2597073.2597076
C. Sadowski, E. Söderberg, L. Church, M. Sipko, A. Bacchelli, (2018). Modern code review: A case study at Google, in Proc. 40th Int. Conf. Software Engineering: Software Engineering in Practice (ICSE-SEIP), 181–190. https://doi.org/10.1145/3183519.3183525
Z. Yang, C. Gao, Z. Guo, Z. Li, K. Liu, X. Xia, and Y. Zhou, A survey on modern code review: Progresses, challenges and opportunities. arXiv preprint arXiv:2405.18216. https://doi.org/10.48550/arXiv.2405.18216
Z. Li, S. Lu, D. Guo, N. Duan, S. Jannu, G. Jenks, D. Majumder, J. Green, A. Svyatkovskiy, S. Fu, N. Sundaresan, (2022). Automating code review activities by large-scale pre-training, in Proc. 30th ACM Joint European Software Engineering conference and symposium. Foundations of Software Engineering (ESEC/FSE), 1035-1047. https://doi.org/10.1145/3540250.3549081
R. Tufano, S. Masiero, A. Mastropaolo, L. Pascarella, D. Poshyvanyk, and G. Bavota, (2022) Using pre-trained models to boost code review automation, In Proceedings of the 44th international conference on software engineering, 2291-2302. https://doi.org/10.1145/3510003.3510621
J. Lu, L. Yu, X. Li, L. Yang, C. Zuo, (2023). Llama-reviewer: Advancing code review automation with large language models through parameter-efficient fine-tuning. In 2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE), IEEE, Florence, Italy. https://doi.org/10.1109/ISSRE59848.2023.00026
C. Pornprasit, C. Tantithamthavorn, (2024).Fine-tuning and prompt engineering for large language models-based code review automation. Information and Software Technology, 175, 107523. https://doi.org/10.1016/j.infsof.2024.107523
A. Naik, M. Alenius, D. Fried, C. Rose, (2025). CRScore: Grounding automated evaluation of code review comments in claims and code changes. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, Albuquerque, New Mexico. https://doi.org/10.18653/v1/2025.naacl-long.457
C. Liu, H.Y. Lin, P. Thongtanunam, (2025), December. Hallucinations in Code Change to Natural Language Generation: Prevalence and Evaluation of Detection Metrics. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Mumbai, India. https://doi.org/10.18653/v1/2025.ijcnlp-long.137
U. Cihan, V. Haratian, A. İçöz, M.K. Gül, Ö. Devran, E.F. Bayendur, B.M. Uçar, E. Tüzün, (2024). Automated code review in practice. In Proceedings of the 2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), IEEE, Ottawa, ON, Canada. https://doi.org/10.1109/ICSE-SEIP66354.2025.00043
H.Y. Lin, P. Thongtanunam, C. Treude, W. Charoenwet, (2024). Improving automated code reviews: Learning from experience. In Proceedings of the 21st International Conference on Mining Software Repositories, 278-283. https://doi.org/10.1145/3643991.3644910
Copyright (c) 2026 Manojpraphakar T, Kannammal K.E, Sasikala P, Kalandhar Naina Mohamed S
This work is licensed under a Creative Commons Attribution 4.0 International License.
Views: Abstract : 6 | PDF : 1
Plum Analytics
.png){kind=logo}
.png)
.png)
.png)
