Rethinking the Methodology of Pair Programming in the Context of Intelligent Agent Integration
Keywords:
pair programming, AI-assisted programming, intelligent agents, human–AI collaboration, software development, code generation, large language modelsAbstract
This article examines the transformation of pair programming methodology in the context of integrating intelligent assistants based on large language models. The study is conducted as a structured narrative review and analytical synthesis of academic publications devoted to AI-assisted programming, human–AI collaboration, and collaborative software development. The main focus is on changes in the structure of developer interaction, the redistribution of roles, and the reconfiguration of cognitive functions between human participants and intelligent agents. Key characteristics of traditional and AI-assisted pair programming are compared, including differences in evaluation parameters, learning effects, and behavioural outcomes. It is shown that the influence of intelligent assistants is not limited to improving productivity, but is realised through changes in the organisation and perception of the development process. It is also demonstrated that isolated use of AI tools does not fundamentally alter collaborative practices unless they are integrated into a coherent interaction structure. An original model of AI-integrated pair programming is proposed, describing the distributed nature of solution generation, evaluation, and refinement within a human–AI system. The results make it possible to consider pair programming as a hybrid form of collaboration, where the effectiveness of development depends on the coordination between human and intelligent components. The article may be of interest to software engineering researchers, educators in computing disciplines, and developers of AI-supported programming tools.
References
[1]. Alanazi, M., Soh, B., Samra, H., & Li, A. (2025). The influence of artificial intelligence tools on learning outcomes in computer programming: A systematic review and meta-analysis. Computers, 14(5), 185. https://doi.org/10.3390/computers14050185
[2]. Ali, F., Ahmed, A., Alipour, M. A., et al. (2025). Adoption of AI-coding assistants in programming education: Exploring trust and learning motivation through an extended technology acceptance model. Journal of Computer Education. https://doi.org/10.1007/s40692-025-00375-w
[3]. Fan, G., Liu, D., Zhang, R., et al. (2025). The impact of AI-assisted pair programming on student motivation, programming anxiety, collaborative learning, and programming performance: A comparative study with traditional pair programming and individual approaches. International Journal of STEM Education, 12, 16. https://doi.org/10.1186/s40594-025-00537-3
[4]. Gaitantzi, A., & Kazanidis, I. (2025). The role of artificial intelligence in computer science education: A systematic review with a focus on database instruction. Applied Sciences, 15(7), 3960. https://doi.org/10.3390/app15073960
[5]. Graßl, I., & Fraser, G. (2023). The ABC of pair programming: Gender-dependent attitude, behavior and code of young learners. arXiv. https://doi.org/10.48550/arXiv.2304.08940
[6]. Jiang, L., Yamaguchi, S., & Bin Ahmadon, M. A. (2025). SynergyAI: A human–AI pair programming tool based on dataflow. Information, 16(3), 178. https://doi.org/10.3390/info16030178
[7]. Kosar, T., Ostojić, D., Liu, Y. D., & Mernik, M. (2024). Computer science education in ChatGPT era: Experiences from an experiment in a programming course for novice programmers. Mathematics, 12(5), 629. https://doi.org/10.3390/math12050629
[8]. Kotsiantis, S., Verykios, V., & Tzagarakis, M. (2024). AI-assisted programming tasks using code embeddings and transformers. Electronics, 13(4), 767. https://doi.org/10.3390/electronics13040767
[9]. Ma, Q., Wu, T., & Koedinger, K. (2023). Is AI the better programming partner? Human–human pair programming vs. human–AI pAIr programming. arXiv. https://doi.org/10.48550/arXiv.2306.05153
[10]. Song, A., & Azman, A. (2025). Leveraging symmetry in multi-agent code generation: A cross-verification collaboration protocol for competitive programming. Symmetry, 17(10), 1660. https://doi.org/10.3390/sym17101660
[11]. Sonkin, V., & Tudose, C. (2025). Beyond snippet assistance: A workflow-centric framework for end-to-end AI-driven code generation. Computers, 14(3), 94. https://doi.org/10.3390/computers14030094
[12]. Valový, M. (2023). Psychological aspects of pair programming. arXiv. https://doi.org/10.48550/arXiv.2306.07421
[13]. Zhang, H., Cheng, W., Wu, Y., & Hu, W. (2024). A pair programming framework for code generation via multi-plan exploration and feedback-driven refinement. arXiv. https://doi.org/10.48550/arXiv.2409.05001
[14]. Zhou, X., Liang, P., Zhang, B., Li, Z., Ahmad, A., Shahin, M., & Waseem, M. (2023). Exploring the problems, their causes and solutions of AI pair programming: A study on GitHub and Stack Overflow. arXiv. https://doi.org/10.48550/arXiv.2311.01020
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Sergei Kuznetsov
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who submit papers with this journal agree to the following terms.
