Source code generation using large language models: a systematic review of the vibe coding methodology

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

This systematic review presents an analysis of the "Vibe Coding" methodology — a contemporary approach to the iterative software development process using Large Language Models (LLMs). Code generation tools are transforming software development by enabling programmers to formulate tasks and describe the desired behavior of software in natural language, while LLMs generate source code corresponding to these requests. The review systematizes current methodologies for the use of LLMs, highlights application examples, evaluates the effectiveness of generated code, discusses emerging challenges, and outlines future development trends of the technology. The aim of this work is to provide a comprehensive understanding of the capabilities and limitations of Vibe Coding as a transformational methodology in software engineering.

Full Text

Restricted Access

About the authors

A. T. Dzhonov

National Research University Higher School of Economics

Author for correspondence.
Email: adzhonov@hse.ru

Graduate Student

Russian Federation, Moscow

S. M. Avdoshin

National Research University Higher School of Economics

Email: savdoshin@hse.ru

Cand. of. Tech. Sc., Professor

Russian Federation, Moscow

References

  1. Elmanov I. V. Engineering approach to AI: use of Spec Driven Development for validation of Vibe Coding, Vestnik nauki, 2025, vol. 4, no. 12 (93), pp. 716—723 (in Russian).
  2. Hou W., Ji Z. Comparing Large Language Models and Human Programmers for Generating Programming Code, Advanced Science, 2025, vol. 12, no. 8, 12 p., doi: 10.1002/advs.202412279.
  3. Wan В. Evaluating Large Language Models for Code Generation: А Comparative Study on Python, Java, and Swift, Applied and Computational Engineering, 2025, vol. 146, pp. 109—126, doi: 10.54254/2755-2721/2025.TJ22242.
  4. Alexandrova T. V. Improving the efficiency of project management in organizations based on the Agile methodology, Ekonomika i biznes: teoriya i praktika, 2019, no. 9, pp. 11—15 (in Russian).
  5. Shinkarev A. A., Yadryshnikova M. V., Loginovskiy O. V., Lazareva S. A., Gubin V. M. Evolution of the use and application of machine learning and artificial intelligence in the development of corporate information systems and decision support systems, Vestnik Yuzhno-Ural’skogo gosudarstvennogo universiteta. Series: Computer Technologies, Control, Radioelectronics, 2025, vol. 25, no. 4, pp. 17—42 (in Russian).
  6. Shneider P. A., Chernysheva A. V., Nikiforova A. D., Govorov A. I., Khlopotov M. V. Study of the effectiveness of prompt engineering and quantized LLMs in creating academic course structures, Kompyuternye instrumenty v obrazovanii, 2024, no. 1, pp. 32—44 (in Russian).
  7. Mathews N. S., Nagappan M. Test-driven development and llm-based code generation, Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering, ASE ’24, 2024, pp. 1583—1594, doi: 10.1145/3691620.3695527.
  8. Zhu-Tian C., Xiong Z., Yao X., Glassman E. Sketch Then Generate: Providing Incremental User Feedback and Guiding LLM Code Generation through Language-Oriented Code Sketches, arxiv.org, 2024, 5 p., doi: 10.48550/arXiv.2405.03998.
  9. Li J., Li G., Li Y., Jin Z. Structured Chain-of-Thought Prompting for Code Generation, ACM Transactions on Software Engineering and Methodology, 2023, vol. 34, no. 2, 12 p., doi: 10.13140/RG.2.2.33742.43848.
  10. Mozharovskiy E. A., Aluev A. S., Dudak A. A., Ishankhonov А. Yu. U. Application of large language models for automation of software testing and debugging, Modern Science: Actual Problems of Theory and Practice. Series: Natural and Technical Sciences, 2024, no. 11-2, p. 103 (in Russian).
  11. Rybachenko I. A. Application of LLM agents for automated code review, Youth and Modern Information Technologies: Proceedings of the XXII International Scientific and Practical Conference of Students, Postgraduates and Young Scientists, April 15—17, 2025, Tomsk, Tomsk Polytechnic University, 2025 (in Russian).
  12. Serebrennikov A. V., Kharisov А. R. Automated event analysis system using local LLM models, Vestnik nauki, 2026, vol. 4, no. 1 (94), pp. 1132—1139 (in Russian).
  13. Vyatkin A. A., Oliseenko V. D. Generation of pandas code for answering questions over large tables using LLMs, International Conference on Soft Computing and Measurements, Saint Petersburg State Electrotechnical University "LETI" named after V. I. Ulyanov (Lenin), 2025, vol. 1, pp. 195—198 (in Russian).
  14. Siddiq M., Santos S., Tanvir R. et al. Exploring the Effectiveness of Large Language Models in Generating Unit Tests, arxiv.org, 2023, 13 p., doi: 10.48550/arXiv.2305.00418.
  15. Abtahi S., Azim А. Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements, arxiv.org, 2025, 11 p., doi: 10.48550/arXiv.2506.10330.
  16. David А. A. Evaluation of the correctness of neural network—generated code: a probabilistic approach, Trudy Instituta sistemnogo programmirovaniya RAN, 2026, vol. 38, no. 2, pp. 111—128 (in Russian).
  17. Akhrameeva K. A., Gerling E. Yu., Mitskovsky D. Yu., Prudnikov S. V. Use of BLEU metric for evaluating naturalness of text in linguistic stegosystems, Vestnik Rossiyskogo novogo universiteta. Series: Complex Systems: Models, Analysis and Management, 2020, no. 2, pp. 73—80.
  18. Avdoshin S. M., Arutyunov G. A. Review of neural network methods for code analysis and generation, Informatsionnye Tehnologii, 2022, vol. 28, no. 7, pp. 378—391, doi: 10.17587/it.28.378-391 (in Russian).
  19. Ren S., Guo D., Lu S. et al. CodeBLEU: a Method for Automatic Evaluation of Code Synthesis, arxiv.org, 2020, 12 p., doi: 10.48550/arXiv.2009.10297.
  20. Inkizhekov А. A. Improving text generation using Retrieval-Augmented Generation, Engineering Technologies: Traditions, Innovations, and Development Vectors. Proc. of the 10th All-Russian Scientific and Practical Conf. with International Participation, 2024, pp. 27—29 (in Russian).

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2026 Informacionnye Tehnologii


СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № 77 - 15565 от 02 июня 2003 г.