Principles of using AI agents in the construction of software code templates

Authors

DOI:

https://doi.org/10.18372/2073-4751.85.21089

Keywords:

AI agents, code generation, software templates, multi-agent systems, software development automation, DevOps integration

Abstract

The paper is devoted to the study of principles for using AI agents in the construction of software code templates under conditions of increasing complexity of modern software systems. The relevance of the topic is determined by the limitations of traditional code generation approaches, such as the lack of contextual consistency, instability of results, and insufficient quality control. The study analyzes modern approaches to programming automation, including template-based methods, neural network models, and large language models (LLMs), and also examines the concepts of multi-agent systems in software engineering.

A formalization of the code template generation problem is proposed as a mapping of a set of requirements, context, and technology stack into a structured software template. A concept of a multi-level agent-based system is developed, which includes analysis, planning, generation, validation, and optimization agents interacting within an iterative process.

A system of principles for constructing such a system is formulated, including the principles of contextual awareness, multi-level generation, iterative validation, modularity, and integration with DevOps processes. The architecture of the system and the algorithm of its operation are proposed, taking into account direct, feedback, and contextual data flows.

To evaluate the effectiveness of the proposed approach, a formalized multi-criteria model is developed, enabling theoretical comparison with alternative solutions. The obtained results can be used in the development of intelligent programming support systems and the automation of software development processes.

References

Chen, M., Tworek, J., Jun, H., et al. Evaluating Large Language Models Trained on Code. arXiv preprint. DOI: https://doi.org/10.48550/arXiv.2107.03374

Nijkamp, E., Hayashi, H., Xie, C., et al. CodeGen: An Open Large Language Model for Code Generation. ACM Transactions on Machine Learning Research, 2023. DOI: https://doi.org/10.48550/arXiv.2203.13474

Li, Y., Wang, S., Wang, H., et al. Competition-Level Code Generation with AlphaCode. Science, 2022. DOI: https://doi.org/10.1126/science.abq1158

Rozière, B., Lachaux, M.-A., Chanussot, L., Lample, G. Code Llama: Open Foundation Models for Code. arXiv / Meta AI, 2023. DOI: https://doi.org/10.48550/arXiv.2308.12950

Austin, J., Odena, A., Nye, M., et al. Program Synthesis with Large Language Models. NeurIPS, 2023. DOI: https://doi.org/10.48550/arXiv.2108.07732

Zhang, F., Chen, X., Wan, Y., et al. CodeT5+: Open Code Large Language Models for Code Understanding and Generation. IEEE Transactions on Software Engineering, 2024. DOI: https://doi.org/10.48550/arXiv.2308.12950

Guo, D., Tang, D., Duan, N., et al. GraphCodeBERT: Pre-training Code Representations with Data Flow. ICLR / IEEE applications, використовується у 2023–2025. DOI: https://doi.org/10.48550/arXiv.2009.08366

Wang, Y., Wang, W., Joty, S., Hoi, S. CodeGeeX: A Pre-trained Model for Code Generation. KDD / ACM, 2023. DOI: https://doi.org/10.1145/3580305.3599790

Yin, P., Neubig, G. A Syntactic Neural Model for General-Purpose Code Generation. ACL / IEEE usage, актуалізовано в нових роботах. DOI: https://doi.org/10.18653/v1/P17-1041

Dong, Y., Chen, X., Wan, Y., et al. Coder Reviewer Reranking for Code Generation. ACL Findings, 2023. DOI: https://doi.org/10.18653/v1/2023.findings-acl.313

Xi, Z., Chen, W., Guo, X., et al. The Rise and Potential of Large Language Model Based Agents: A Survey. arXiv, 2023. DOI: https://doi.org/10.48550/arXiv.2309.07864

Wang, L., Ma, Y., Zhang, X., et al. A Survey on Large Language Model Based Autonomous Agents. Frontiers of Computer Science, 2024. DOI: https://doi.org/10.1007/s11704-024-3309-2

Park, J. S., O’Brien, J. C., Cai, C. J., et al. Generative Agents: Interactive Simulacra of Human Behavior. ACM UIST, 2023. DOI: https://doi.org/10.1145/3586183.3606763

Hong, S., Zhu, Y., Chen, X., et al. MetaGPT: Meta Programming for Multi-Agent Collaborative Framework. arXiv, 2023. DOI: https://doi.org/10.48550/arXiv.2308.00352

Qian, C., Cong, X., Yang, W., et al. Communicative Agents for Software Development. arXiv, 2023. DOI: https://doi.org/10.48550/arXiv.2307.07924

Pearce, H., Ahmad, B., Tan, B., et al. Asleep at the Keyboard? Assessing the Security of GitHub Copilot. IEEE Symposium on Security and Privacy, 2023. DOI: https://doi.org/10.1109/SP46215.2023.10179387

Vaithilingam, P., Zhang, T., Glassman, E. Expectation vs Reality: Evaluating AI Code Generation Tools. CHI Conference, 2023. DOI: https://doi.org/10.1145/3544548.3581382

Barke, S., James, M. B., Polikarpova, N. Grounded Copilot: How Programmers Interact with Code-Generating Models. OOPSLA / ACM, 2023. DOI: https://doi.org/10.1145/3586030

Sobania, D., Briesch, M., Hanna, C., et al. An Analysis of Code Generation by ChatGPT. IEEE Access, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3273868

Dakhel, A. M., Majdinasab, V., Nikanjam, A., et al. GitHub Copilot AI Pair Programmer: Asset or Liability? Journal of Systems and Software, 2023. DOI: https://doi.org/10.1016/j.jss.2023.111734

Downloads

Published

2026-04-28

How to Cite

Artamonov, Y., Petrenko, S., Zhultynska, A., & Plotytsia, S. (2026). Principles of using AI agents in the construction of software code templates. Problems of Informatization and Control, 1(85). https://doi.org/10.18372/2073-4751.85.21089

Issue

Vol. 1 No. 85 (2026)

Section

Статті

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The scientific journal adheres to the principles of Open Access and provides free, immediate, and permanent access to all published materials without financial, technical, or legal barriers for readers.

All articles are published in Open Access under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.

Copyright

Authors who publish their works in the journal:

  • retain the copyright to their publications;

  • grant the journal the right of first publication of the article;

  • agree to the distribution of their materials under the CC BY 4.0 license;

  • have the right to reuse, archive, and distribute their works (including in institutional and subject repositories), provided that proper reference is made to the original publication in the journal.