Pull-Request Whisperer: LLM-Enhanced RCA Advisory Bot for Developers
Keywords:
root-cause analysis, large language models, pull requests, continuous integration, semantic matchingAbstract
The objective of this research is to present an improved software quality assurance, Pull-Request Whisperer employs large language models (LLMs) coupled to continuous integration (CI) pipelines to advise on root-cause analysis (RCA). The bot analyses code changes by using historical incident embeddings based on defects to validate pull requests. Extensive semantic matching and anomaly detection locate pull requests that resemble problematic code.
Downloads
References
M. Weiser, “Program slicing,” Proceedings of the 5th International Conference on Software Engineering, 1981, pp. 439–449.
J. A. Jones and M. J. Harrold, “Empirical evaluation of the tarantula automatic fault-localization technique,” Proceedings of the 20th IEEE/ACM International Conference on Automated Software Engineering, 2005, pp. 273–282.
S. Yoo and M. Harman, “Regression testing minimization, selection and prioritization: a survey,” Software Testing, Verification and Reliability, vol. 22, no. 2, pp. 67–120, 2012.
M. R. Prasad, M. Burke, and D. Notkin, “Using dynamic information to improve software inspection effectiveness,” Proceedings of the 20th International Conference on Software Engineering, 1998, pp. 393–402.
J. Corbett et al., “Debugging distributed systems,” Proceedings of the 2004 ACM SIGOPS/EuroSys European Conference on Computer Systems, 2004, pp. 74–87.
T. Zimmermann, P. Weißgerber, S. Diehl, and A. Zeller, “Mining version histories to guide software changes,” IEEE Transactions on Software Engineering, vol. 31, no. 6, pp. 429–445, 2005.
T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” arXiv preprint arXiv:1301.3781, 2013.
O. Vinyals, S. Bengio, and M. Kudlur, “Order matters: Sequence to sequence for sets,” International Conference on Learning Representations (ICLR), 2016.
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
M. Allamanis, E. T. Barr, P. Devanbu, and C. Sutton, “A survey of machine learning for big code and naturalness,” ACM Computing Surveys (CSUR), vol. 51, no. 4, pp. 1–37, 2018.
R. C. Holt, “Software fault prediction: Techniques and applications,” International Conference on Software Engineering Advances, 2015, pp. 1–6.
T. Menzies, J. Greenwald, and A. Frank, “Data mining static code attributes to learn defect predictors,” IEEE Transactions on Software Engineering, vol. 33, no. 1, pp. 2–13, 2007.
A. Hindle et al., “On the naturalness of software,” Proceedings of the 34th International Conference on Software Engineering, 2012, pp. 837–847.
R. Gupta, S. Pal, I. Dillig, and A. Aiken, “Deepfix: Fixing common C language errors by deep learning,” Proceedings of the 34th ACM SIGPLAN Conference on Programming Language Design and Implementation, 2013, pp. 3–15.
H. Kagdi, J. P. Corriveau, J. I. Maletic, and M. L. Collard, “Toward an integrated approach to software traceability and regression testing,” Proceedings of the 16th International Conference on Software Engineering and Knowledge Engineering, 2004, pp. 43–50.
R. Holmes and R. J. Walker, “An automated approach to regression testing using static analysis,” IEEE International Conference on Software Maintenance, 2001, pp. 87–96.
M. A. Storey et al., “Improving program comprehension with source code summarization,” International Journal of Software Engineering and Knowledge Engineering, vol. 15, no. 4, pp. 647–669, 2005.
N. Nagappan, T. Ball, and A. Zeller, “Mining metrics to predict component failures,” Proceedings of the 28th International Conference on Software Engineering, 2006, pp. 452–461.
K. Hata, M. Velez, and P. H. Melançon, “Toward automated code review with machine learning: An empirical study on open source projects,” Proceedings of the 40th International Conference on Software Engineering, 2018, pp. 70–80.
A. E. Hassan, “The road ahead for mining software repositories,” Proceedings of the Future of Software Engineering, 2008, pp. 48–57.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
