Skip to content
Electronic Modeling
UKEN
Menu

Artificial Intelligence in Teamwork in Software Engineering

O. Nesterenko, V. Fedorov, P. Yatsuk

Èlektron. model. 2026, 48(5):77-92

Full text (PDF)

Українська версія

Abstract

Artificial intelligence (AI) is becoming an integral part of software engineering, expanding the possibilities for automating software development and maintenance processes throughout its entire life cycle. In today’s environment, the issue of human-machine teaming (HMT)-that is, the interaction between humans and AI as team members-is gaining relevance. This paper analyzes the main challenges associated with human-AI collaboration, particularly with regard to group dynamics methodology. A transformation of Tuckman’s model is proposed, which allows for describing the evolution of software engineering teams as a process of co-development between humans and AI. An extension of Belbin’s role model is also proposed, leading to the formation of a hybrid role-distribution system in software engineering teams integrated with AI. As a result, an integrated framework has been developed that combines the team development stage model, the role model, and the capabilities of AI, allowing software engineering teams to be described as hybrid socio-technical systems. A conceptual model of AI-supported teamwork and its detailed representation using UML diagrams are proposed. The results of this study confirm that AI is becoming an intellectual partner to the team. This leads to a transformation of team interaction and its future development.

Keywords

human-machine interaction, group dynamics, Tuckman model, Belbin model, UML, intellectualization, software

References

  1. Kokol, P. (2024). The use of AI in software engineering: A synthetic knowledge synthesis of the recent research literature. Information, 15(6), 354. https://doi.org/10.3390/info15060354
  2. Pai, H. A., Sharath, K. R., & Babalad, K. (2025). Integrating AI into software engineering: A critical review and future directions. In Proceedings of the 2025 International Conference on Intelligent Control, Computing and Communications (IC3) (p. 20-25). https://doi.org/10.1109/IC363308.2025.10957449
  3. Nesterenko, O., & Selin, Y. (2021). The teams information model for software engineering management. In Proceedings of the 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT) (1, p. 341-344). https://doi.org/10.1109/CSIT52700.2021.9648737
  4. Schleiger, E., Mason, C., Naughtin, C., et al. (2024). Collaborative Intelligence: A Scoping Review of Current Applications. Applied Artificial Intelligence, 38(1), e2327890. https://doi.org/10.1080/08839514.2024.2327890
  5. Shi, M., Wang, G., Zhang, S., et al. (2025). AISCW: Artificial Intelligence Supported Cooperative Work the New Frontier of CSCW. In Sun, H., et al. (ed.). Computer Supported Cooperative Work and Social Computing. ChineseCSCW 2024. Communications in Computer and Information Science, 2343 (p. 3-17). Springer, Singapore. https://doi.org/10.1007/978-981-96-2373-0_1
  6. Nesterenko, O., & Yatsuk, P. (2025). AI (not) against AI. Environmental Safety and Natural Resources, 56(4), 134-153. https://doi.org/10.32347/2411-4049.2025.4.134-153. (in Ukrainian).
  7. Cao, S., Sun, X., Widyasari, R., et al. (2025). A systematic literature review on explainability for ML/DL-based software engineering. ACM Computing Surveys, 58(4), Article 95, 1-34. https://doi.org/10.1145/3763230
  8. Alami, A., & Ernst, N. (2025). Human and machine: How software engineers perceive and engage with AI-assisted code reviews compared to their peers. In Proceedings of the 2025 IEEE/ACM 18th International Conference on Cooperative and Human Aspects of Software Engineering (CHASE) (p. 63-74). https://doi.org/10.1109/CHASE66643.2025.00016
  9. Desolda, G., Esposito, A., Lanzilotti, R., Piccinno, A. (2025). Designing and Evaluating Human-Centred AI Systems: Best-Practices from a Multidisciplinary View. CEUR Workshop Proceedings, 3957, 170-178.
  10. Ronanki, K. (2025). Facilitating trustworthy human-agent collaboration in LLM-based multi-agent system oriented software engineering. In Companion proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering (FSE 2025). arXiv. https://doi.org/10.48550/arXiv.2505.04251
  11. Trinkenreich, B., Calefato, F., Hanssen, G., et al. (2025). Get on the train or be left on the station: Using LLMs for software engineering research. In Companion proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering (FSE Companion 2025) (p. 1503-1507). https://doi.org/10.1145/3696630.3731666
  12. Stutz, K., Sandkuhl, K., & Möhring, M. (2026). Empirical insights into the usage of generative AI in software engineering. Lecture Notes in Business Information Processing, 562 (p. 257-271). https://doi.org/10.1007/978-3-032-04375-7_16
  13. Fischer, M., & Lanquillon, C. (2024). Evaluation of generative AI-assisted software design and engineering: A user-centered approach. Lecture Notes in Computer Science, 14734 (p. 31-47). https://doi.org/10.1007/978-3-031-60606-9_3
  14. Ulfsnes, R., Moe, N. B., Emmerhoff, J., et al. (2025). Responsible AI in agile software engineering: An industry perspective. Lecture Notes in Business Information Processing, 524 (p. 33-41). https://doi.org/10.1007/978-3-031-72781-8_4
  15. Ain, Q. U., Haq, M., Jilani, A. A. A., & Sohail, K. (2025). A comparison between traditional software engineering practices and AI-driven methodologies. Generative AI in Software Engineering (p. 57-92). https://doi.org/10.4018/979-8-3373-0370-3.ch002.
  16. Fan, A., Gokkaya, B., Harman, M., et al. (2023). Large language models for software engineering: Survey and open problems. In Proceedings of the 2023 IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FOSE) (p. 31-53). https://doi.org/10.1109/ICSE-FoSE59343.2023.00008
  17. Tantithamthavorn, C., & Jiarpakdee, J. (2021). Explainable AI for software engineering. In Proceedings of the 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE 2021) (p. 1-2). https://doi.org/10.1109/ASE51524.2021.9678580
  18. Rauf, I., Sharp, H., Lopez, T., & Wermelinger, M. (2025). Human-machine teaming and team effectiveness in AI tools for software engineering. In Proceedings of the 2025 Conference on Cooperative and Human Aspects of Software Engineering (CHASE) (p. 75-80). https://doi.org/10.1109/CHASE66643.2025.00017
  19. Abrahão, S., Grundy, J., Pezzè, M., et al. (2025). Software Engineering by and for Humans in an AI Era. ACM Transactions on Software Engineering and Methodology, 34 (5), art. no. 129. https://doi.org/10.1145/3715111
  20. Trofymchuk, O., Nesterenko, O., & Netesin, I. (2022). Methodology for Designing Analytical Information Systems for Administrative Management. Science and Innovation, 18(4), 25-40. https://doi.org/10.15407/scine18.04.025. [in Ukrainian].
  21. Kaelin, V. C., Tewari, M., Benouar, S., & Lindgren, H. (2024). Developing teamwork: Transitioning between stages in human-agent collaboration. Frontiers in Computer Science, 6. https://doi.org/10.3389/fcomp.2024.1455903
  22. Brajković, D.Ć., Brajković, E., Volarić, T. (2026). Application of the Random Forest Algorithm for Team Role Classification Based on Belbin’s Self-perception Inventory. In Proceedings of the 3rd International Conference on Digital Transformation in Education and Artificial Intelligence Applications, MoStart 2025 (2609 CCIS, p. 283-294). https://doi.org/10.1007/978-3-032-02801-3_19
  23. Lhazmir, H., Samhale, S., Louzaoui, K., & Benlhachmi, K. (2025). The uneven journey of AI in software testing: A maturity model for industry adoption. In Proceedings of the 3rd International Conference on Digital Transformation in Education and Artificial Intelligence Applications, MoStart 2025 (2609 CCIS, p. 132-137). https://doi.org/10.1109/CiSt65886.2025.11224099.

Received 16.04.2026