Large Language Models for Automated Software Code Generation, Optimization, and Bug Detection
Keywords:
Large Language Models, Artificial Intelligence, Code Generation, Code Optimization, Bug Detection, Generative AI, Software Engineering, Automated Programming.Abstract
Large Language Models (LLMs) have emerged as an important advancement in Artificial Intelligence, particularly in the field of automated software engineering. Their ability to understand natural-language instructions and generate programming code has created new opportunities for automating software development activities. This paper investigates the application of LLMs in three important areas of software engineering: automated code generation, code optimization, and bug detection. The proposed approach establishes an integrated LLM-based workflow in which software requirements expressed in natural language are transformed into source code, followed by automated validation, optimization, and defect identification. The methodology combines prompt-based generation with static analysis and automated testing to improve the reliability of generated programs. The evaluation framework considers functional correctness, code quality, execution efficiency, bug-detection capability, and testing effectiveness. The study also examines the limitations of LLM-based programming, including hallucinated code, logical inconsistencies, security vulnerabilities, and incorrect interpretation of requirements. Rather than replacing software developers, LLMs are considered intelligent programming assistants that can reduce repetitive development effort and support developers during different stages of the software development lifecycle. The proposed framework provides a systematic foundation for evaluating LLM-assisted programming and highlights the importance of combining generative AI with automated validation and human supervision.
Downloads
References
1. A. Vaswani et al., “Attention Is All You Need,” Advances in Neural Information Processing Systems, vol. 30, 2017.
2. T. Brown et al., “Language Models are Few-Shot Learners,” Advances in Neural Information Processing Systems, vol. 33, pp. 1877–1901, 2020.
3. M. Chen et al., “Evaluating Large Language Models Trained on Code,” arXiv preprint arXiv:2107.03374, 2021.
4. D. Hendrycks et al., “Measuring Coding Challenge Competence With HumanEval,” arXiv preprint arXiv:2107.03374, 2021.
5. M. Le et al., “CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation,” Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 8696–8708, 2021.
6. Y. Wang et al., “CodeT5+: Open Code Large Language Models for Code Understanding and Generation,” arXiv preprint arXiv:2305.07922, 2023.
7. D. Fried et al., “InCoder: A Generative Model for Code Infilling and Synthesis,” International Conference on Learning Representations, 2023.
8. Vishram Singh, 2026. "Enterprise Resource Planning for Financial Applications: Engineering, Architecture, and Design Principles," Int J Sci Res Sci Technol, International Journal of Scientific Research in Science and Technology, vol. 13(2), pages 653-661, April.
9. N. Shinn et al., “Reflexion: Language Agents with Verbal Reinforcement Learning,” Advances in Neural Information Processing Systems, 2023.
10. S. P. P. et al., “Large Language Models for Software Engineering: A Systematic Literature Review,” ACM Computing Surveys, 2024.
11. M. Fan et al., “Large Language Models for Code Generation: A Survey,” ACM Transactions on Software Engineering and Methodology, 2024.
12. B. Xia et al., “Automated Program Repair with Large Language Models,” Proceedings of the IEEE/ACM International Conference on Software Engineering, 2024.
13. J. Li et al., “StarCoder: May the Source Be With You!” Transactions on Machine Learning Research, 2023.
14. R. Nijkamp et al., “CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis,” International Conference on Learning Representations, 2023.
15. Singh, V. (2026). Real-Time Financial Data Validation Platform for Enterprise Accounting Systems. International Journal of Computer Information Systems and Industrial Management Applications, 18(10s), 467-481.
16. Vishram Singh. (2026). Prompt Context Caching Architecture for Cost Reduction in Large Language Model Systems. International Journal of Intelligent Systems and Applications in Engineering, 14(1s), 1543 –. Retrieved from https://www.ijisae.org/index.php/IJISAE/article/view/8385
17. Todupunuri, A. (2025). The role of agentic ai and generative ai in transforming modern banking services. American Journal of AI Cyber Computing Management, 5(3), 85-93.
18. Todupunuri, A. (2025). The role of human-centric AI in building trust in digital banking ecosystems. International Journal of Innovative Science and Research Technology, 10(1), 1281-1286.
19. Bajarang Bhagwat, V. (2023). Optimizing Payroll to General Ledger Reconciliation: Identifying Discrepancies and Enhancing Financial Accuracy. JOURNAL OF ADVANCE AND FUTURE RESEARCH, 1 (4).
20. Bhagwat, V. B. (2025). Simplifying Payroll Balance Conversions in Payroll Systems Implementation through the Use of Generative AI.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ashwini. H (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
