Agentic AI for Autonomous Software Maintenance: A Retrieval-Augmented Multi-Agent Framework for Bug Localization, Patch Generation, and Regression Validation
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V7I2P134Keywords:
Agentic AI, Autonomous Software Maintenance, Retrieval-Augmented Generation, Bug Localization, Automated Program Repair, Regression Validation, Multi-Agent Systems, CI/CD GovernanceAbstract
Autonomous software maintenance is becoming a critical research direction as modern codebases grow beyond the practical reach of manual debugging, release governance, and regression validation. Large language models have demonstrated strong code-generation capabilities, but repository-level maintenance remains difficult because defects frequently arise from interactions among multiple files, hidden dependencies, runtime configurations, and incomplete issue reports. This paper proposes AutoMaint-RAG, a retrieval-augmented multi-agent framework for autonomous software maintenance. The framework coordinates specialized agents for issue interpretation, repository retrieval, fault localization, patch synthesis, static analysis, test generation, regression execution, and release-risk governance. Unlike single-agent code-generation workflows, AutoMaint-RAG treats maintenance as a controlled software-engineering process in which every generated patch must be grounded in repository evidence, ranked suspicious locations, executable test feedback, and auditable decision records. The proposed framework integrates hybrid retrieval over code, commit history, test traces, dependency graphs, and operational telemetry; combines spectrum-based fault localization with semantic ranking; and applies iterative patch refinement through execution-guided feedback. A reproducible validation protocol is defined using repository-level issue benchmarks, mutation-based regression assessment, and industrial-style CI/CD gates. The paper contributes a formal architecture, agent-interaction protocol, patch-risk scoring model, evaluation design, and governance layer for deploying agentic AI in safety-sensitive software maintenance environments. The central argument is that autonomous maintenance should not be reduced to prompt-based patch generation; rather, it requires an engineered socio-technical pipeline that constrains language-model creativity through retrieval grounding, tool execution, regression evidence, and human-review escalation. The proposed framework advances a research agenda for maintainable, auditable, and operationally reliable AI agents in software lifecycle management.
References
[1] Jimenez, C. E., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., & Narasimhan, K. (2023). SWE-bench: Can language models resolve real-world GitHub issues? arXiv:2310.06770.
[2] Sivva, S. D., Thalakanti, R. R., Bandari, S. S. G., & Yettapu, S. D. R. (2023). AI-Driven Decision Intelligence for Agile Software Lifecycle Governance: An Architecture-Centered Framework Integrating Machine Learning Defect Prediction and Automated Testing. International Journal of Emerging Trends in Computer Science and Information Technology, 4(4), 167-172. https://doi.org/10.63282/3050-9246.IJETCSIT-V4I4P118
[3] Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2023). ReAct: Synergizing Reasoning and Acting in Language Models. International Conference on Learning Representations.
[4] Thalakanti, R. R., & Goud Bandari, S. S. (2024). Intelligent Continuous Integration and Delivery for Banking Systems using Machine Learning Driven Risk Detection with Real World Deployment Evaluation. International Journal of AI, BigData, Computational and Management Studies, 5(4), 168-175. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V5I4P118
[5] Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems.
[6] Gudi, S. R. (2024). Design and Evaluation of Secure Microservices Architecture for HIPAA-Compliant Prescription Processing on AWS and OpenShift. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 5(2), 144-149. https://doi.org/10.63282/3050-9262.IJAIDSML-V5I2P116
[7] Yang, J., Jimenez, C. E., Wettig, A., Lieret, K., Yao, S., Narasimhan, K., & Press, O. (2024). SWE-agent: Agent-computer interfaces enable automated software engineering. arXiv:2405.15793.
[8] A. K. K. V. Alluri and S. Barde, “AI Powered Decision Intelligence Frameworks for Predictive and Prescriptive Business Optimization in Salesforce Enterprise Platforms,” 2026 International Conference on Electronic Systems and Intelligent Computing (ICESIC), Chennai, India, 2026, pp. 438-443, doi: 10.1109/ICESIC67389.2026.11496409
[9] Raikar, T. and Apelagunta, V. (2025). Implementing SAP Fiori in S/4HANA Transitions: Key Guidelines, Challenges, Strategic Implications, AI Integration Recommendations. Journal of Engineering Research and Sciences, 4(11), 1–9. https://doi.org/10.55708/js0411001
[10] T. Raikar, “Preserving the clean core principles in SAP systems: Design strategies for integrating AI,” 2026 International Conference on Electronic Systems and Intelligent Computing (ICESIC), Chennai, India, 2026, pp. 1036–1041, doi: 10.1109/ICESIC67389.2026.11496501
[11] Gunda, S. K. (2025). AI-Enhanced API Reliability Testing for Digital Banking: Improving Accuracy, Resilience, and Integrity in Financial Transaction Processing. International Journal of Emerging Trends in Computer Science and Information Technology, 6(2), 136-143. https://doi.org/10.63282/3050-9246.IJETCSIT-V6I2P116
[12] Mansur, E., et al. (2025). RAGFix: Enhancing LLM Code Repair Using RAG and Dynamic Retrieval. arXiv preprint.
[13] S. Yalamati, “Sparse Matrix Factorization for Scalable Machine Learning in Cloud Environments,” 2025 International Conference on NexGen Networks and Cybernetics (IC2NC), Erode, India, 2025, pp. 333-338, doi: 10.1109/IC2NC67409.2025.11376338
[14] Raikar, T. (2025). High-Performance In-Memory Computing: A Research Study on SAP S/4 HANA Database Layer. American Journal of Technology, 4(2), 93–113. https://doi.org/10.58425/ajt.v4i2.449
[15] Bandari, S. S. G., Sivva, S. D., & Thalakanti, R. R. (2024). Regulatory Grade Fraud Detection using Explainable Artificial Intelligence with Auditable Decision Pathways and Empirical Validation on Banking Data. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 5(3), 139-147. https://doi.org/10.63282/3050-9262.IJAIDSML-V5I3P115
[16] Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023). Reflexion: Language Agents with Verbal Reinforcement Learning. Advances in Neural Information Processing Systems.
[17] Mutyam, N. (2024). Graph-based modeling of service dependencies for predicting failure propagation in distributed systems. International Journal of Multidisciplinary Evolutionary Research, 5(1), 113–116. https://doi.org/10.54660/IJMER.2024.5.1.113-116
[18] Gudi, S. R. (2023). Enhancing Reliability in Java Enterprise Systems through Comparative Analysis of Automated Testing Frameworks. International Journal of Emerging Trends in Computer Science and Information Technology, 4(2), 151-160. https://doi.org/10.63282/3050-9246.IJETCSIT-V4I2P115
[19] Zhang, Y., Ruan, H., Fan, Z., & Roychoudhury, A. (2024). AutoCodeRover: Autonomous Program Improvement. arXiv: 2404.05427
[20] Reddy Mittamidi, V. K. (2025). Leveraging AI and ML for Predictive Monitoring and Error Mitigation in Change Data Capture Pipelines. International Journal of Emerging Trends in Computer Science and Information Technology, 6(3), 104-111. https://doi.org/10.63282/3050-9246.IJETCSIT-V6I3P116
[21] Gunda, S. K. G. (2023). The Future of Software Development and the Expanding Role of ML Models. International Journal of Emerging Research in Engineering and Technology, 4(2), 126-129. https://doi.org/10.63282/3050-922X.IJERET-V4I2P113
[22] Ridnik, T., Kredo, D., & Friedman, I. (2024). Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering. arXiv:2401.08500
[23] Naik, S., Aitharaju, P., & Bandari, S.S. (2025). AI Chatbots in Enterprise Solutions: Transforming Customer Support, Industry-Specific Challenges and Ethical Considerations. Glovento Journal of Integrated Studies.
[24] Raikar, T. (2026, March). Ethics of AI-based supply chain optimization: A better balance between efficiency and fairness. https://doi.org/10.55670/fpll.futech.5.2.26
[25] Abreu, R., Zoeteweij, P., Golsteijn, R., & van Gemund, A. J. C. (2009). A practical evaluation of spectrum-based fault localization. Journal of Systems and Software, 82(11), 1780–1792.
[26] Kishore Varma Alluri, A. K. (2025). Using Salesforce CRM and Deep Learning (CNN) Techniques to Improve Patient Journey Mapping and Engagement in Small and Medium Healthcare Organizations. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 6(4), 101-109. https://doi.org/10.63282/3050-9262.IJAIDSML-V6I4P115
[27] M. Ukey, S. R. Abbidi, T. K. Kota, T. Raikar, M. Mallepati, and P. J. Adinarayana, “Digital transformation in healthcare: Integrating clinical research with data management technologies,” in Proc. 2026 6th Int. Conf. Recent Trends Comput. Sci. Technol. (ICRTCST), Jamshedpur, India, 2026, pp. 886–891, doi: 10.1109/ICRTCST68392.2026.11545210
[28] Gudi, S. R. (2024). Leveraging Predictive Analytics and Redis-Backed Caching to Optimize Specialty Medication Fulfillment and Pharmacy Inventory Management. International Journal of AI, BigData, Computational and Management Studies, 5(3), 155-160. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V5I3P116
[29] Badertdinov, I., Golubev, A., Nekrashevich, M., Shevtsov, A., Karasik, S., Andriushchenko, A., Trofimova, M., Litvintseva, D., & Yangel, B. (2025). SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents. arXiv: 2505.20411.
[30] S. K. Gunda, “Comparative Analysis of Machine Learning Models for Software Defect Prediction,” 2024 International Conference on Power, Energy, Control and Transmission Systems (ICPECTS), Chennai, India, 2024, pp. 1-6, https://doi.org/10.1109/ICPECTS62210.2024.10780167
[31] S. Yalamati, “Reinforcement Learning for Dynamic Service Composition in Edge Networks,” 2025 4th International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India, 2025, pp. 1158-1163, doi: 10.1109/ICAAIC64647.2025.11330768
[32] Thalakanti, R. R., Goud Bandari, S. S., & Sivva, S. D. . (2024). Federated Learning for Privacy Preserving Fraud Detection across Financial Institutions: Architecture Protocols and Operational Governance. International Journal of Emerging Research in Engineering and Technology, 5(2), 108-114. https://doi.org/10.63282/3050-922X.IJERET-V5I2P111
[33] Le Goues, C., Pradel, M., & Roychoudhury, A. (2019). Automated Program Repair. Communications of the ACM, 62(12), 56–65.
[34] Balerao, M. (2023). A converged artificial intelligence architecture for innovation, software lifecycle optimization, and cybersecurity risk mitigation. International Journal of Multidisciplinary Futuristic Development, 4(1), 117–120. https://doi.org/10.54660/IJMFD.2023.4.1.117-120
[35] S. R. Gudi, “Monitoring and Deployment Optimization in Cloud-Native Systems: A Comparative Study Using OpenShift and Helm,” 2025 4th International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Tirupur, India, 2025, pp. 792-797, https://doi.org/10.1109/ICIMIA67127.2025.11200594
[36] Gunda SK, Yettapu SDR, Bodakunti S, Bikki SB. Decision Intelligence Methodology for AI-Driven Agile Software Lifecycle Governance and Architecture-Centered Project Management, 2023 Mar. 30;4(1):102-8. https://doi.org/10.63282/3050-9262.IJAIDSML-V4I1P112
[37] Tao, Y., Qin, Y., & Liu, Y. (2025). Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches. arXiv:2510.04905.
[38] R. R. Thalakanti, “Convergence Analysis and Implementation of Linear Multistep Methods for Solving Ordinary Differential Equations,” 2025 2nd Asian Conference on Intelligent Technologies (ACOIT), KOLAR, India, 2025, pp. 1-18, doi: 10.1109/ACOIT66109.2025.11436783
[39] AI-Driven API Architectures for Multi-Cloud Enterprises: A Comparative Study of Centralized, Distributed, and Hybrid Deployment Models. (2026). International Journal of Computer Science and Engineering Innovations, 2(1), 60-67. https://doi.org/10.64137/31079458/IJCSEI-V2I1P108
[40] Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., Yang, Y., Gupta, S., Majumder, B. P., Hermann, K., Welleck, S., Yazdanbakhsh, A., & Clark, P. (2023). Self-Refine: Iterative Refinement with Self-Feedback. arXiv:2303.17651.
[41] Bandari, S. S. G., Banda, S., & Naik, S. “Machine Learning (ML) based Anomaly Detection in Insurance Industries.” Journal of Information Systems Engineering and Management 10(32s), 2026. https://doi.org/10.52783/jisem.v10i32s.5182
[42] R. R. Thalakanti, “Formalizing feature model integrity: a typing system and refactoring approaches for improving software product line design,” International Conference on Advancing Technology in Engineering and Science (ICATES 2025), Mumbai, India, 2026, pp. 710-717, doi: 10.1049/icp.2025.4792
[43] Zhang, S., Ding, Y., Lian, S., Song, S., & Li, H. (2025). CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion. arXiv:2509.16112
[44] Gudi, S. R. (2024). AI-Driven Fax-to-Digital Prescription Automation: A Cloud-Native Framework Using OCR, Machine Learning, and Microservices for Pharmacy Operations. International Journal of Emerging Research in Engineering and Technology, 5(1), 111-116. https://doi.org/10.63282/3050-922X.IJERET-V5I1P113
[45] S. K. Gunda, “Fault Prediction Unveiled: Analyzing the Effectiveness of Random Forest, Logistic Regression, and KNeighbors,” 2024 2nd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), Erode, India, 2024, pp. 107-113, https://doi.org/10.1109/ICSSAS64001.2024.10760620
[46] S. Yalamati, “Probabilistic Reasoning in Multi-Agent Reinforcement Learning Systems,” 2025 International Conference on NexGen Networks and Cybernetics (IC2NC), Erode, India, 2025, pp. 707-712, doi: 10.1109/IC2NC67409.2025.11376303
[47] Sivva, S. D. (2023). An end-to-end AI-based systems engineering paradigm for lifecycle governance, predictive quality assurance, automation economics, and cybersecurity intelligence. Journal of Frontiers in Multidisciplinary Research, 4(1), 600–604. https://doi.org/10.54660/.JFMR.2023.4.1.600-604
[48] Wang, J., He, Y., & Chen, H. (2024). RepoGenReflex: Enhancing Repository-Level Code Completion with Verbal Reinforcement and Retrieval-Augmented Generation. arXiv:2409.13122
[49] S. R. Gudi, “Deconstructing Monoliths: A Fault-Aware Transition to Microservices with Gateway Optimization using Spring Cloud,” 2025 6th International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 2025, pp. 815-820, https://doi.org/10.1109/ICESC65114.2025.11212326
[50] R. R. Thalakanti, “Optimizing Neural Network Architecture for Binary Classification Using Evolutionary Algorithms,” 2025 International Conference on Electronics and Computing, Communication Networking Automation Technologies (ICEC2NT), Pune, India, 2025, pp. 1-6, doi: 10.1109/ICEC2NT65402.2025.11380048
[51] Gunda, S. K. (2025). Predictive Validation of Banking APIs and Transaction Workflows Using Machine Learning-Based Defect Detection Model. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 6(1), 284-292. https://doi.org/10.63282/3050-9262.IJAIDSML-V6I1P133
[52] Xia, C. S., & Zhang, L. (2024). Keep the Conversation Going: Fixing 162 out of 337 Bugs for $0.42 Each Using ChatGPT. Proceedings of the ACM SIGSOFT International Symposium on Software Testing and Analysis.
[53] Kishore Varma Alluri, A. K. (2026). Governed Agentic AI for Salesforce CRM Platforms: A Reference Architecture for Data Grounding, Decision Intelligence, Trust Controls, and Lifecycle Reliability. International Journal of Emerging Trends in Computer Science and Information Technology, 7(1), 374-382. https://doi.org/10.63282/3050-9246.IJETCSIT-V7I1P153
[54] Gudi, S. R. (2025). Enhancing optical character recognition (OCR) accuracy in healthcare prescription processing using artificial neural networks. European Journal of Artificial Intelligence and Machine Learning, 4(6). https://doi.org/10.24018/ejai.2025.4.6.79
[55] S. Yalamati, “AI-Augmented Service Fabric for Adaptive Resource Management in Cloud Environments,” 2025 5th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS), Erode, India, 2025, pp. 963-968, doi: 10.1109/ICUIS67429.2025.11380548
[56] Sai Krishna Gunda; An exploration of adaptive ensemble approaches in software fault detection: Balancing accuracy and robustness. AIP Conf. Proc. 7 January 2026; 3345 (1): 020211. https://doi.org/10.1063/5.0298093
[57] R. R. Thalakanti, “Enhancing Convergence in Fully Connected Neural Networks via Optimized Backpropagation,” 2025 2nd International Conference on Computing and Data Science (ICCDS), Chennai, India, 2025, pp. 1-6, doi: 10.1109/ICCDS64403.2025.11209625
[58] Basaveni Siri Mallika Rao, Sai Santosh Goud Bandari, “Replacing AI Agents for Backend,” International Journal of Scientific Research in Engineering and Management. vol. https://doi.org/10.55041/IJSREM.NCFT011
[59] S. R. Gudi, “Ensuring Secure and Compliant Fax Communication: Anomaly Detection and Encryption Strategies for Data in Transit,” 2025 4th International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), Tirupur, India, 2025, pp. 786-791, https://doi.org/10.1109/ICIMIA67127.2025.11200537
[60] Gunda, S. K. (2024). An Intelligent AI-Driven Framework for Real-Time ATM Transaction Validation, Fraud Detection and Financial Switching Integrity. International Journal of Emerging Research in Engineering and Technology, 5(4), 180-191. https://doi.org/10.63282/3050-922X.IJERET-V5I4P119
[61] A. K. K. V. Alluri, “A Systematic Study of Machine Learning Frameworks Enabling Scalable Secure and Explainable Artificial Intelligence in Salesforce CRM Platforms,” 2026 International Conference on Electronic Systems and Intelligent Computing (ICESIC), Chennai, India, 2026, pp. 396-401, doi: 10.1109/ICESIC67389.2026.11496486
[62] Manga, I., Sivva, S. D. ., & Manga, V. K. (2024). The Adaptive Intelligence in Cloud Systems: A Unified Architecture for AI Enhanced Observability and Automated Root Cause Analysis. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 5(1), 160-166. https://doi.org/10.63282/3050-9262.IJAIDSML-V5I1P115
[63] Gunda, S. K. (2025). A Scalable AI-Driven Quality Engineering Architecture for End-To-End Validation of Core Banking, API, and UAT Ecosystems. American International Journal of Computer Science and Technology, 7(6), 126-138. https://doi.org/10.63282/3117-5481/AIJCST-V7I6P113
[64] S. Yalamati, “Energy-Efficient Task Offloading in Multi-Tenant Edge Clouds,” 2026 International Conference on Electronic Systems and Intelligent Computing (ICESIC), Chennai, India, 2026, pp. 379-384, doi: 10.1109/ICESIC67389.2026.11496473
[65] Kishore Varma Alluri, A. K. . (2025). Salesforce CRM Framework for Real Time DeFi Portfolio Intelligence and Customer Engagement Forecasting in Web3 Based Decentralized Finance Ecosystems Using ML Techniques. International Journal of AI, BigData, Computational and Management Studies, 6(4), 99-107. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V6I4P111
[66] Gunda, S. K. (2025). Accelerating Scientific Discovery With Machine Learning and HPC-Based Simulations. In B. Ben Youssef & M. Ben Ismail (Eds.), Integrating Machine Learning Into HPC-Based Simulations and Analytics (pp. 229-252). IGI Global Scientific Publishing. https://doi.org/10.4018/978-1-6684-3795-7.ch009
[67] Reddy Mittamidi, V. K. (2025). AI/ML Powered Intelligent Root Cause Analysis and Automated Remediation for Multi System Data Integrity Issues. International Journal of AI, BigData, Computational and Management Studies, 6(4), 133-141. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V6I4P115
[68] Gazzola, L., Micucci, D., & Mariani, L. (2019). Automatic Software Repair: A Survey. IEEE Transactions on Software Engineering, 45(1), 34–67.
[69] Krishna, G. V., Reddy, B. D., & Vrindaa, T. (2025). EmoVision: An Intelligent Deep Learning Framework for Emotion Understanding and Mental Wellness Assistance in Human Computer Interaction. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 6(4), 14-20. https://doi.org/10.63282/3050-9262.IJAIDSML-V6I4P103
[70] Gunda, S.K. (2026). A Hybrid Deep Learning Model for Software Fault Prediction Using CNN, LSTM, and Dense Layers. In: Bakaev, M., et al. Internet and Modern Society. IMS 2025. Communications in Computer and Information Science, vol 2672. Springer, Cham. https://doi.org/10.1007/978-3-032-05144-8_21
[71] Srikanth Reddy Gudi. (2025). A Comparative Analysis of Pivotal Cloud Foundry and OpenShift Cloud Platforms. The American Journal of Applied Sciences, 7(07), 20–29. https://doi.org/10.37547/tajas/Volume07Issue07-03
[72] S. K. Gunda, “Automatic Software Vulnerabilty Detection Using Code Metrics and Feature Extraction,” 2025 2nd International Conference On Multidisciplinary Research and Innovations in Engineering (MRIE), Gurugram, India, 2025, pp. 115-120, https://doi.org/10.1109/MRIE66930.2025.11156601
[73] V. K. R. Mittamidi, “An Automated AI-Driven Monitoring and Observability Framework for Cloud-Based Data Pipelines by Software Defect Prediction Research,” International Journal of Multidisciplinary Evolutionary Research, vol. 5, no. 1, pp. 109-112, 2024, doi: 10.54660/IJMER.2024.5.1.109-112
[74] S. K. Gunda, “Analyzing Machine Learning Techniques for Software Defect Prediction: A Comprehensive Performance Comparison,” 2024 Asian Conference on Intelligent Technologies (ACOIT), KOLAR, India, 2024, pp. 1-5, https://doi.org/10.1109/ACOIT62457.2024.10939610
