Next-Generation AI-Assisted Bug Tracking and Automated Code Analysis System

DOI

10.2991/978-94-6239-713-2_55How to use a DOI?

Keywords

Bug Tracking System; Static Code Analysis; ESL int; SonarQube; Artificial Intelligence

Abstract

Bug tracking is a time-consuming activity in current software development, which generally involves manual bug reporting, bug triage, and bug propagation. In large and fast-evolving projects, this manual dependency causes slowing down bug resolution, duplicating reports, inconsistency in labeling severity, and overburdening developers. This paper introduces an AI-assisted bug tracking and automated code analysis system that aims at lowering human participation in the process of defect management. The system combines widely used static code analysis applications – ESLint and SonarQube – with our custom-built parsing modules, an XGBoost-based severity classifier, a hybrid Sentence-BERT duplicate detector, and a retrieval augmentation-based fix recommendation module, to automatically predict the severity of bugs, approximate their priority, identify duplicate bug reports, and provide fix recommendations from past fixed cases. The experimental results show that the proposed system produces 91.4% classification accuracy of bugs, 65% reduction of triage time (42.3 minutes to 14.8 minutes), and 23% reduction of duplicate report submissions which surpasses two traditional systems, Jira, Bugzilla, and YouTrack, and machine learning baselines such as Naive Bayes (78.2%), SVM (82.6%), CNN (85.1%), and Distil BERT (88.7), and all results are statistically significant p¡0.001. The main contribution of this work is the development of a fully-integrated end-to-end pipeline that unifies the automated static code analysis and the AI-supported triage done by the human developer into a single CI-CD deployable system that provides measurable success in terms of the quality of software defect resolution and developer productivity compared to the traditional manual tracking approach.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Priya Pandey
AU  - Aniket Kumar
AU  - Aditya Singh
AU  - Shruti Kumari
PY  - 2026
DA  - 2026/06/25
TI  - Next-Generation AI-Assisted Bug Tracking and Automated Code Analysis System
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 741
EP  - 758
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_55
DO  - 10.2991/978-94-6239-713-2_55
ID  - Pandey2026
ER  -