The Evolution of Cognitive Software Engineering: A Longitudinal Analysis of Large Language Models and Machine Learning in Architectural Synthesis, Fault Prediction, and Code Comprehension
Keywords:
Neural Code Comprehension, Large Language Models, Software Architecture, Fault PredictionAbstract
The landscape of software engineering is currently undergoing a fundamental paradigm shift, transitioning from manual, heuristic-driven development to an automated, cognitive-centric model powered by Large Language Models (LLMs) and Machine Learning (ML). This research article provides an extensive investigation into the integration of neural code comprehension and generative artificial intelligence across the software development lifecycle. By synthesizing contemporary advancements in architectural pattern detection, fault prediction, and automated code repair, this study elucidates how modern AI architectures-ranging from bilateral tree-based convolutional neural networks to transformer-based few-shot learners-are redefining the boundaries of software assurance and system design. We examine the transition from traditional source code metrics to learnable representations of code semantics, discussing the implications of neuro-symbolic program correctors and graph-based generative modeling. Furthermore, the paper addresses the emerging role of LLMs in identifying architectural smells, refactoring microservices, and maintaining consistency in low-code platforms. Through a rigorous analysis of existing empirical evidence and theoretical frameworks, this research identifies a critical "automation gap" in software architecting and proposes a trajectory for future autonomous systems. The findings suggest that while AI significantly enhances productivity and fault detection, issues regarding software fairness, carbon footprints, and the nuances of cross-language algorithm classification remain pivotal challenges for the next decade of academic and industrial pursuit.
References
An, J., Ding, W., & Lin, C. (2023). ChatGPT: tackle the growing carbon footprint of generative AI. Nature, 615, 586.
Ben-Nun, T., Jakobovits, A. S., & Hoefler, T. (2018). Neural code comprehension: A learnable representation of code semantics. Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS ’18), 3589-3601.
Bhandari, G. P., & Gupta, R. (2018). Machine learning based software fault prediction utilizing source code metrics. 2018 IEEE 3rd International Conference on Computing, Communication and Security (ICCCS), 40-45.
Bhatia, S., Kohli, P., & Singh, R. (2018). Neuro-symbolic program corrector for introductory programming assignments. Proceedings of the 40th International Conference on Software Engineering (ICSE ’18), 60-70.
Bielik, P., Raychev, V., & Vechev, M. T. (2017). Program synthesis for character level language modeling. ICLR.
Bilgin, Z., Ersoy, M. A., Soykan, E. U., Tomur, E., Çomak, P., & Karaçay, L. (2020). Vulnerability prediction from source code using machine learning. IEEE Access, 8, 150672-150684.
Black, P. E. (2007). Software assurance with SAMATE reference dataset, tool standards, and studies.
Boland, F., & Black, P. (2012). The Juliet 1.1 C/C++ and Java test suite. IEEE Computer, 45, 10.1109/MC.2012.345.
Bowes, D., Hall, T., Harman, M., Jia, Y., Sarro, F., & Wu, F. (2016). Mutation-aware fault prediction. Proceedings of the 25th International Symposium on Software Testing and Analysis (ISSTA 2016), 330-341.
Braga, R., Neto, P. S., Rabêlo, R., Santiago, J., & Souza, M. (2018). A machine learning approach to generate test oracles. Proceedings of the XXXII Brazilian Symposium on Software Engineering (SBES ’18), 142-151.
Brauckmann, A., Goens, A., Ertel, S., & Castrillon, J. (2020). Compiler-based graph representations for deep learning models of code. Proceedings of the 29th International Conference on Compiler Construction (CC 2020), 201-211.
Brockschmidt, M., Allamanis, M., & Gaunt, A. L. (2019). Generative code modeling with graphs. International Conference on Learning Representations (ICLR).
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. arXiv preprint arXiv:2005.14165.
Bruch, M., Monperrus, M., & Mezini, M. (2009). Learning from examples to improve code completion systems. Proceedings of the 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering (ESEC/FSE ’09), 213-222.
Brun, Y., & Meliou, A. (2018). Software fairness. Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2018), 754-759.
Bui, N. D. Q., Jiang, L., & Yu, Y. (2018). Cross-language learning for program classification using bilateral tree-based convolutional neural networks. AAAI Workshops.
Bui, N. D. Q., Yu, Y., & Jiang, L. (2019). Bilateral dependency neural networks for cross-language algorithm classification. 2019 IEEE 26th International Conference on Software Analysis, Evolution and Reengineering (SANER), 422-433.
Butgereit, L. (2019). Using machine learning to prioritize automated testing in an agile environment. 2019 Conference on Information Communications Technology and Society (ICTAS), 1-6.
Cai, J., Shin, R., & Song, D. (2017). Making neural programming architectures generalize via recursion. CoRR, abs/1704.06611.
Cai, C. H., Sun, J., & Dobbie, G. (2019). Automatic B-model repair using model checking and machine learning. Automated Software Engineering, 26(3), 10.1007/s10515-019-00264-4.
Cambronero, J. P., & Rinard, M. C. (2019). AL: autogenerating supervised learning programs. Proceedings of the ACM on Programming Languages, 3(OOPSLA), 1-28.
Caram, F. L., Rodrigues, B. R. O., Campanelli, A. S., & Parreiras, F. S. (2019a). Machine learning techniques for code smells detection: a systematic mapping study. International Journal of Software Engineering and Knowledge Engineering, 29(02), 285-316.
Duarte, C. E. (2025). Automated microservice pattern instance detection using infrastructure-as-code artifacts and large language models. 2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C), 161-166.
Eisenreich, T., Speth, S., & Wagner, S. (2024). From requirements to architecture: An ai-based journey to semi-automatically generate software architectures. Proceedings of the 1st International Workshop on Designing Software, 52-55.
Fauzan, R., Siahaan, D., Rochimah, S., & Triandini, E. (2024). Structural similarity assessment for multiple UML diagrams measurement with UML common graph. AIP Conference Proceedings, 2927(1).
Feng, Y., Vanam, S., Cherukupally, M., Zheng, W., Qiu, M., & Chen, H. (2023). Investigating code generation performance of ChatGPT with crowdsourcing social data. 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), 876–885.
Fuchs, D., Liu, H., Hey, T., Keim, J., & Koziolek, A. (2025). Enabling architecture traceability by llm-based architecture component name extraction. 2025 IEEE 22nd International Conference on Software Architecture (ICSA), 1-12.
Hagel, N., Hili, N., Bartel, A., & Koziolek, A. (2025). Towards llm-powered consistency in model-based low-code platforms. 2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C), 364-369.
K. S. Hebbar, “MACHINE LEARNING-ASSISTED SERVICE BOUNDARY DETECTION FOR MODULARIZING LEGACY SYSTEMS,” International Journal of Applied Engineering & Technology, vol. 04, no.02, pp. 401-414, Sep. 2022, https://romanpub.com/resources/ijaet-v4-2-2022-48.pdf
Ivers, J., & Ozkaya, I. (2025). Will generative ai fill the automation gap in software architecting? 2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C), 41-45.
Jahić, J., & Sami, A. (2024). State of practice: Llms in software engineering and software architecture. 2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C), 311–318.
Johansson, N., Caporuscio, M., & Olsson, T. (2024). Mapping source code to software architecture by leveraging large language models. Software Architecture. ECSA 2024 Tracks and Workshops, 133-149.
Larsen, K. R., & Edvall, M. (2024). Investigating the impact of generative ai on newcomers’ understanding of software projects.
Liu, C. L., Ho, C. T., & Wu, T. C. (2024). Custom GPTs enhancing performance and evidence compared with GPT-3.5, GPT-4, and GPT-4o? A study on the emergency medicine specialist examination. Healthcare, 12(17), 1726.
Lutze, R., & Waldhör, K. (2024). Generating specifications from requirements documents for smart devices using large language models (llms). Human-Computer Interaction, Springer Nature Switzerland, 94-108.
Maranhão, J. J., & Guerra, E. M. (2024). A prompt pattern sequence approach to apply generative ai in assisting software architecture decision-making. Proceedings of the 29th European Conference on Pattern Languages of Programs, People, and Practices (EuroPLoP ’24).
Miño, J., Andrade, R., Torres, J., & Chicaiza, K. (2024). Leveraging generative artificial intelligence for software antipattern detection. Information Management.
Nayak, M. (2024). How is the Artificial Intelligence of Today's Time, ChatGPT and Blackbox. ai, Helpful in Machine Learning?. ChatGPT and Blackbox. ai, Helpful in Machine Learning.
Pandini, G., Martini, A., Videsjorden, A. N., & Fontana, F. A. (2025). An exploratory study on architectural smell refactoring using large languages models. 2025 IEEE 22nd International Conference on Software Architecture Companion (ICSA-C), 462–471.
Quevedo, E., Abdelfattah, A. S., Rodriguez, A., Yero, J., & Cerny, T. (2024). Evaluating chatgpt’s proficiency in understanding and answering microservice architecture queries using source code insights. SN Computer Science, 5, 422.
Suriya, S., & Nivetha, S. (2023). Design of UML Diagrams for WEBMED-Healthcare Service System Services. EAI Endorsed Transactions on E-Learning, 8(1).
Triandini, E., Fauzan, R., Siahaan, D. O., Rochimah, S., Suardika, I. G., & Karolita, D. (2022). Software similarity measurements using UML diagrams: A systematic literature review. Register: Jurnal Ilmiah Teknologi Sistem Informasi, 8(1), 10–23.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Aristhanes K. Vardhaman
This work is licensed under a Creative Commons Attribution 4.0 International License.
