Разработка CASE-платформы с генеративным искусственным интеллектом и агентным слоем модельного контекста

В статье представлена архитектура, реализация и предварительная сервисная оценка прототипа CASE-платформы, использующей генеративный искусственный интеллект для структурирования требований, генерации кода, формирования тестовых артефактов и проверки развёртывания. Платформа объединяет адаптерный слой интеграции с большой языковой моделью, версионное хранилище артефактов, явные контрольные точки подтверждения пользователем и двунаправленный слой модельного контекста (MCP) для инструментальной интеграции. Оценка ограничена воспроизводимым детерминированным-режимом, регрессионными тестами серверной части, сравнением свойств рабочего процесса с двумя базовыми режимами и дополнительной разведочной проверкой с реальным коммерческим поставщиком языковой модели на двух проектных запросах. Результаты дают предварительные свидетельства архитектурной реализуемости трассируемого процесса от требований к артефактам, но не доказывают промышленную готовность решения или семантическую корректность всей сгенерированной бизнес-логики.

1. Brambilla M., Cabot J., Wimmer M. Model-Driven Software Engineering in Practice. Synthesis Lectures on Software Engineering. Morgan & Claypool, 2012, 182 p. DOI: 10.2200/S00441ED1V01Y201208SWE001.

2. da Silva A.R. Model-driven engineering: A survey supported by a unified conceptual model. Computer Languages, Systems & Structures, 2015, vol. 43, pp. 139-155. DOI: 10.1016/j.cl.2015.06.001.

3. Fan A., Gokkaya B., Harman M., Lyubarskiy M., Sengupta S., Yoo S., Zhang J.M. Large Language Models for Software Engineering: Survey and Open Problems. In Proc. of the IEEE/ACM International Conference on Software Engineering: Future of Software Engineering (ICSE-FoSE), 2023, pp. 31-53. DOI: 10.1109/ICSE-FoSE59343.2023.00008.

4. Hou X., Zhao Y., Liu Y., Yang Z., Wang K., Li L., Luo X., Lo D., Grundy J., Wang H. Large Language Models for Software Engineering: A Systematic Literature Review. ACM Transactions on Software Engineering and Methodology, 2024, vol. 33, no. 8, article 220. DOI: 10.1145/3695988.

5. Zhang Q., Fang C., Xie Y., Zhang Y., Yang Y., Sun W., Yu S., Chen Z. A Survey on Large Language Models for Software Engineering. Science China Information Sciences, 2026, vol. 69, article 141102. DOI: 10.1007/s11432-025-4670-0.

6. Vaithilingam P., Zhang T., Glassman E.L. Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models. In Proc. of the CHI Conference on Human Factors in Computing Systems, 2022, article 332, pp. 1-18. DOI: 10.1145/3491101.3519665.

7. Pearce H., Ahmad B., Tan B., Dolan-Gavitt B., Karri R. Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions. In Proc. of the IEEE Symposium on Security and Privacy, 2022, pp. 754-768. DOI: 10.1109/SP46214.2022.9833571.

8. Li Y., Choi D., Chung J., Kushman N., Schrittwieser J., Leblond R., Eccles T., et al. Competition-level code generation with AlphaCode. Science, 2022, vol. 378, no. 6624, pp. 1092-1097. doi: 10.1126/science.abq1158.

9. Chen M., Tworek J., Jun H., Yuan Q., Pinto H.P.O., Kaplan J., Edwards H., et al. Evaluating Large Language Models Trained on Code. Preprint, 2021. DOI: 10.48550/arXiv.2107.03374.

10. Poesia G., Polozov O., Le V., Tiwari A., Soares G., Meek C., Gulwani S. Synchromesh: Reliable code generation from pre-trained language models. In Proc. of the International Conference on Learning Representations, 2022.

11. Nijkamp E., Pang B., Hayashi H., Tu L., Wang H., Zhou Y., Savarese S., Xiong C. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. In Proc. of the International Conference on Learning Representations, 2023.

12. Fried D., Aghajanyan A., Lin J., Wang S., Wallace E., Shi F., Zhong R., et al. InCoder: A Generative Model for Code Infilling and Synthesis. In Proc. of the International Conference on Learning Representations, 2023.

13. Arora C., Sabetzadeh M., Briand L.C., Zimmer F. Machine learning and natural language processing for requirements engineering: A systematic mapping study. ACM Computing Surveys, 2022, vol. 54, no. 3, article 55. DOI: 10.1145/3444689.

14. Zadenoori M.A., Dabrowski J., Alhoshan W., Zhao L., Ferrari A. Large Language Models for Requirements Engineering: A Systematic Literature Review. Preprint, 2025. DOI: 10.48550/arXiv.2509.11446.

15. Siddiq M.L., Santos J.C.S., Tanvir R.H., Ulfat N., Al Rifat F., Lopes V.C. Using Large Language Models to Generate JUnit Tests: An Empirical Study. In Proc. of the International Conference on Evaluation and Assessment in Software Engineering (EASE), 2024, pp. 313-322. DOI: 10.1145/3661167.3661216.

16. Schäfer M., Nadi S., Eghbali A., Tip F. An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation. IEEE Transactions on Software Engineering, 2024, vol. 50, no. 1, pp. 85-105. DOI: 10.1109/TSE.2023.3334955.

17. Fraser G., Arcuri A. EvoSuite: Automatic Test Suite Generation for Object-Oriented Software. In Proc. of the ACM SIGSOFT Symposium and the European Conference on Foundations of Software Engineering, 2011, pp. 416-419. DOI: 10.1145/2025113.2025179.

18. Lukasczyk S., Kroiss F., Fraser G. Automated Unit Test Generation for Python. In Proc. of the International Symposium on Search Based Software Engineering, 2020, pp. 9-24. DOI: 10.1007/978-3-030-59762-7_2.

19. Hong S., Zhuge M., Chen J., Zheng X., Cheng Y., Zhang C., Wang J., et al. MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework. In Proc. of the International Conference on Learning Representations, 2024.

20. Qian C., Liu W., Liu H., Chen N., Dang Y., Li J., Yang C., Chen W., Su Y., Cong X., Xu J., Li D., Liu Z., Sun M. ChatDev: Communicative Agents for Software Development. In Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024, pp. 15174-15186. DOI: 10.18653/v1/2024.acl-long.810.

21. Tufano M., Agarwal A., Jang J., Moghaddam R.Z., Sundaresan N. AutoDev: Automated AI-Driven Development. Preprint, 2024. DOI: 10.48550/arXiv.2403.08299.

22. Yang J., Jimenez C.E., Wettig A., Lieret K., Yao S., Narasimhan K., Press O. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. In Advances in Neural Information Processing Systems, 2024.

23. Jimenez C.E., Yang J., Wettig A., Yao S., Pei K., Press O., Narasimhan K. SWE-bench: Can Language Models Resolve Real-World GitHub Issues? In Proc. of the International Conference on Learning Representations, 2024.

24. Yao S., Zhao J., Yu D., Du N., Shafran I., Narasimhan K., Cao Y. ReAct: Synergizing Reasoning and Acting in Language Models. In Proc. of the International Conference on Learning Representations, 2023.

25. Shinn N., Cassano F., Gopinath A., Narasimhan K., Yao S. Reflexion: Language Agents with Verbal Reinforcement Learning. In Advances in Neural Information Processing Systems, 2023, vol. 36.

26. Madaan A., Tandon N., Gupta P., Hallinan S., Gao L., Wiegreffe S., Alon U., et al. Self-Refine: Iterative Refinement with Self-Feedback. In Advances in Neural Information Processing Systems, 2023.

27. Schick T., Dwivedi-Yu J., Dessi R., Raileanu R., Lomeli M., Hambro E., Zettlemoyer L., Cancedda N., Scialom T. Toolformer: Language Models Can Teach Themselves to Use Tools. In Advances in Neural Information Processing Systems, 2023.

28. Patil S.G., Zhang T., Wang X., Gonzalez J.E. Gorilla: Large Language Model Connected with Massive APIs. In Advances in Neural Information Processing Systems, 2024, vol. 37.

29. Li M., Zhao Y., Yu B., Song F., Li H., Yu H., Li Z., Huang F., Li Y. API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs. In Proc. of the Conference on Empirical Methods in Natural Language Processing, 2023, pp. 3102-3116. DOI: 10.18653/v1/2023.emnlp-main.187.

30. Qin Y., Liang S., Ye Y., Zhu K., Yan L., Lu Y., Lin Y., et al. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs. In Proc. of the International Conference on Learning Representations, 2024.

31. Anthropic. Model Context Protocol Specification. 2024-2026. Available at: https://modelcontextprotocol.io/, accessed 07.06.2026.

32. Polygalov B. HSE-CASE-AI: Prototype CASE Platform with Generative AI. GitHub repository, commit dd15d1594301980d4c56f004672a2d30db264df9, 2026. Available at: https://github.com/miamib34ch/HSE-CASE-AI, accessed 07.06.2026.