ArchiGenMS: A Neuro-Symbolic Evolutionary Framework for Greenfield Microservice Design
Resumo
Projetar microsserviços a partir de requisitos greenfield continua sendo desafiador porque artefatos textuais iniciais são ambíguos e a geração com LLMs pode produzir decomposições estruturalmente inconsistentes. Este artigo apresenta o ArchiGenMS, um framework neuro-simbólico que combina exploração semântica guiada por LLMs com um núcleo computável de validação em Lean 4 dentro de um laço evolucionário elitista. O framework opera sobre uma abstração arquitetural inicial de serviços, operações, parâmetros e chamadas entre serviços. Em 22 conjuntos de dados do corpus de Dalpiaz, a porcentagem de candidatos válidos em Lean cresce de 74,5% para 99,5% em cinco gerações, enquanto a proxy média de coesão melhora de 0,29 para 0,23. Esses resultados posicionam o ArchiGenMS como uma abordagem reproduzível e formalmente restrita para descoberta de microsserviços assistida por IA.
Palavras-chave:
Microsserviços, IA Generativa, Verificação Formal, Lean 4, Algoritmos Evolutivos, IA Neuro-simbólica
Referências
Adams, L., Boyle, F., Boyle, P., Amoroso d’Aragona, D., Cerny, T., and Taibi, D. (2023). Chatgpt for microservice development: How far can we go? In International Conference on Microservices.
Al-Debagy, O. and Martinek, P. (2020). A metrics framework for evaluating microservices architecture designs. Journal of Web Engineering, 19(3–4):341–370.
ArchiGenMS Project (2025). ArchiGenMS: Reproducible package. [link]. GitHub Repository.
Bajaj, D., Goel, A., and Gupta, S. C. (2022). Greenmicro: identifying microservices from use cases in greenfield development. IEEE Access, 10:67008–67018.
Battaglia, N., Rossi, G., Fernández, A., and Narváez, D. (2025). Behavior-Driven Microservice Architecture: un marco metodológico para la identificación iterativa de microservicios en proyectos ágiles greenfield. Revista Abierta de Informática Aplicada, 9(1):102–123.
Belzner, L., Gabor, T., and Wirsing, M. (2023). Large language model assisted software engineering: prospects, challenges, and a case study. In International conference on bridging the gap between AI and reality, pages 355–374. Springer.
Chen, M., Tworek, J., Jun, H., Yuan, Q., de Oliveira Pinto, H. P., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., Ray, A., Puri, R., Krueger, G., Petrov, M., Khlaaf, H., Sastry, G., Mishkin, P., Chan, B., Gray, S., Ryder, N., Pavlov, M., Power, A., Kaiser, L., Bavarian, M., Winter, C., Tillet, P., Such, F. P., Cummings, D., Plappert, M., Chantzis, F., Barnes, E., Herbert-Voss, A., Guss, W. H., Nichol, A., Paino, A., Tezak, N., Tang, J., Babuschkin, I., Balaji, S., Jain, S., Saunders, W., Hesse, C., Carr, A. N., Leike, J., Achiam, J., Misra, V., Morikawa, E., Radford, A., Knight, M., Brundage, M., Murati, M., Mayer, K., Welinder, P., McGrew, B., Amodei, D., McCandlish, S., Sutskever, I., and Zaremba, W. (2021). Evaluating large language models trained on code.
Clarke, E. M. and Wing, J. M. (1996). Formal methods: State of the art and future directions. ACM Computing Surveys (CSUR), 28(4):626–643.
Dalpiaz, F. (2018). Requirements data sets (user stories). Mendeley Data. Dataset.
Dhar, R., Vaidhyanathan, K., and Varma, V. (2024). Can llms generate architectural design decisions?-an exploratory empirical study. In 2024 IEEE 21st International Conference on Software Architecture (ICSA), pages 79–89. IEEE.
Díaz-Pace, J. A., Tommasel, A., and Capilla, R. (2024). Helping novice architects to make quality design decisions using an llm-based assistant. In European Conference on Software Architecture, pages 324–332. Springer.
Dragoni, N., Giallorenzo, S., Lafuente, A. L., Mazzara, M., Montesi, F., Mustafin, R., and Safina, L. (2017). Microservices: yesterday, today, and tomorrow. Present and ulterior software engineering, pages 195–216.
Esposito, M., Li, X., Moreschini, S., Ahmad, N., Cerny, T., Vaidhyanathan, K., Lenarduzzi, V., and Taibi, D. (2025). Generative ai for software architecture. applications, trends, challenges, and future directions. arXiv preprint arXiv:2503.13310.
Evans, E. (2004). Domain-driven design: tackling complexity in the heart of software. Addison-Wesley Professional.
Harman, M., Mansouri, S. A., and Zhang, Y. (2012). Search-based software engineering: Trends, techniques and applications. ACM Computing Surveys (CSUR), 45(1):1–61.
Harman, M. and Yao, X. (2010). Software module clustering as a multi-objective search problem. IEEE Transactions on Software Engineering, 37(2):264–282.
Lucassen, G., Dalpiaz, F., van der Werf, J. M. E., and Brinkkemper, S. (2016). Improving agile requirements: the quality user story framework and tool. Requirements engineering, 21(3):383–403.
Mkaouer, W., Kessentini, M., Shaout, A., Koligheu, P., Bechikh, S., Deb, K., and Ouni, A. (2015). Many-objective software remodularization using nsga-iii. ACM Transactions on Software Engineering and Methodology (TOSEM), 24(3):1–45.
Moura, L. d. and Ullrich, S. (2021). The lean 4 theorem prover and programming language. In International Conference on Automated Deduction, pages 625–635. Springer.
Narváez, D. (2025). Explorando el uso de inteligencia artificial en el descubrimiento y diseño de microservicios. In Congresso Ibero-Americano em Engenharia de Software (CIbSE) - Doctoral Symposium, pages 224–231, Ciudad Real, Spain. SBC.
Narváez, D., Battaglia, N., Fernández, A., and Rossi, G. (2025a). Descubrimiento automático de microservicios mediante modelos generativos y verificación formal. In XXXI Congreso Argentino de Ciencias de la Computación (CACIC) (Viedma, 6 al 10 de octubre de 2025), Viedma, Argentina. Universidad Nacional de Río Negro (UNRN).
Narváez, D., Battaglia, N., Fernández, A., and Rossi, G. (2025b). Designing microservices using AI: A systematic literature review. Software, 4(1):6.
Narváez, D., Rossi, G., and Battaglia, N. (2024). Aplicación de inteligencia artificial en el diseño de microservicios. In XXX Congreso Argentino de Ciencias de la Computación (CACIC)(La Plata, 7 al 11 de octubre de 2024).
Neri, D., Soldani, J., Zimmermann, O., and Brogi, A. (2020). Design principles, architectural smells and refactorings for microservices: a multivocal review. SICS Software-Intensive Cyber-Physical Systems, 35(1):3–15.
Newman, S. (2021). Building microservices: designing fine-grained systems. ”O’Reilly Media, Inc.”.
Novikov, A., Vũ, N., Eisenberger, M., Dupont, E., Huang, P.-S., Wagner, A. Z., Shirobokov, S., Kozlovskii, B., Ruiz, F. J., Mehrabian, A., et al. (2025). Alphaevolve: A coding agent for scientific and algorithmic discovery. arXiv preprint arXiv:2506.13131.
Pereira, J. R. A., Albuquerque, D., Perkusich, M., Rodríguez, G., Díaz-Pace, J. A., Gorgônio, K., and Perkusich, A. (2025). Toward generating microservice architectures from textual requirements with large language models. In Simpósio Brasileiro de Componentes, Arquiteturas e Reutilização de Software (SBCARS), pages 79–89. SBC.
Pérez, G., Mostaccio, C., and Antonelli, L. (2025). Análisis comparativo de arquitecturas de nlp para detectar similitudes entre escenarios en español. In Workshop on Requirements Engineering (WER).
Taibi, D., Lenarduzzi, V., Pahl, C., and Janes, A. (2017). Microservices in agile software development: a workshop-based study into issues, advantages, and disadvantages. In Proceedings of the XP2017 Scientific Workshops, pages 1–5.
Taibi, D. and Systä, K. (2019). A decomposition and metric-based evaluation framework for microservices.
Ünlü, H., Kennouche, D. E., Soylu, G. K., and Demirörs, O. (2024). Microservice-based projects in agile world: A structured interview. Information and Software Technology, 165:107334.
Vera-Rivera, F. H., Cuadros, E. G. P., Perez, B., Astudillo, H., and Gaona, C. (2023). Semgromi—a semantic grouping algorithm to identifying microservices using semantic similarity of user stories. PeerJ Computer Science, 9:e1380.
Woods, E., Erder, M., and Pureur, P. (2021). Continuous architecture in practice: Software architecture in the age of agility and DevOps. Addison-Wesley Professional.
Al-Debagy, O. and Martinek, P. (2020). A metrics framework for evaluating microservices architecture designs. Journal of Web Engineering, 19(3–4):341–370.
ArchiGenMS Project (2025). ArchiGenMS: Reproducible package. [link]. GitHub Repository.
Bajaj, D., Goel, A., and Gupta, S. C. (2022). Greenmicro: identifying microservices from use cases in greenfield development. IEEE Access, 10:67008–67018.
Battaglia, N., Rossi, G., Fernández, A., and Narváez, D. (2025). Behavior-Driven Microservice Architecture: un marco metodológico para la identificación iterativa de microservicios en proyectos ágiles greenfield. Revista Abierta de Informática Aplicada, 9(1):102–123.
Belzner, L., Gabor, T., and Wirsing, M. (2023). Large language model assisted software engineering: prospects, challenges, and a case study. In International conference on bridging the gap between AI and reality, pages 355–374. Springer.
Chen, M., Tworek, J., Jun, H., Yuan, Q., de Oliveira Pinto, H. P., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., Ray, A., Puri, R., Krueger, G., Petrov, M., Khlaaf, H., Sastry, G., Mishkin, P., Chan, B., Gray, S., Ryder, N., Pavlov, M., Power, A., Kaiser, L., Bavarian, M., Winter, C., Tillet, P., Such, F. P., Cummings, D., Plappert, M., Chantzis, F., Barnes, E., Herbert-Voss, A., Guss, W. H., Nichol, A., Paino, A., Tezak, N., Tang, J., Babuschkin, I., Balaji, S., Jain, S., Saunders, W., Hesse, C., Carr, A. N., Leike, J., Achiam, J., Misra, V., Morikawa, E., Radford, A., Knight, M., Brundage, M., Murati, M., Mayer, K., Welinder, P., McGrew, B., Amodei, D., McCandlish, S., Sutskever, I., and Zaremba, W. (2021). Evaluating large language models trained on code.
Clarke, E. M. and Wing, J. M. (1996). Formal methods: State of the art and future directions. ACM Computing Surveys (CSUR), 28(4):626–643.
Dalpiaz, F. (2018). Requirements data sets (user stories). Mendeley Data. Dataset.
Dhar, R., Vaidhyanathan, K., and Varma, V. (2024). Can llms generate architectural design decisions?-an exploratory empirical study. In 2024 IEEE 21st International Conference on Software Architecture (ICSA), pages 79–89. IEEE.
Díaz-Pace, J. A., Tommasel, A., and Capilla, R. (2024). Helping novice architects to make quality design decisions using an llm-based assistant. In European Conference on Software Architecture, pages 324–332. Springer.
Dragoni, N., Giallorenzo, S., Lafuente, A. L., Mazzara, M., Montesi, F., Mustafin, R., and Safina, L. (2017). Microservices: yesterday, today, and tomorrow. Present and ulterior software engineering, pages 195–216.
Esposito, M., Li, X., Moreschini, S., Ahmad, N., Cerny, T., Vaidhyanathan, K., Lenarduzzi, V., and Taibi, D. (2025). Generative ai for software architecture. applications, trends, challenges, and future directions. arXiv preprint arXiv:2503.13310.
Evans, E. (2004). Domain-driven design: tackling complexity in the heart of software. Addison-Wesley Professional.
Harman, M., Mansouri, S. A., and Zhang, Y. (2012). Search-based software engineering: Trends, techniques and applications. ACM Computing Surveys (CSUR), 45(1):1–61.
Harman, M. and Yao, X. (2010). Software module clustering as a multi-objective search problem. IEEE Transactions on Software Engineering, 37(2):264–282.
Lucassen, G., Dalpiaz, F., van der Werf, J. M. E., and Brinkkemper, S. (2016). Improving agile requirements: the quality user story framework and tool. Requirements engineering, 21(3):383–403.
Mkaouer, W., Kessentini, M., Shaout, A., Koligheu, P., Bechikh, S., Deb, K., and Ouni, A. (2015). Many-objective software remodularization using nsga-iii. ACM Transactions on Software Engineering and Methodology (TOSEM), 24(3):1–45.
Moura, L. d. and Ullrich, S. (2021). The lean 4 theorem prover and programming language. In International Conference on Automated Deduction, pages 625–635. Springer.
Narváez, D. (2025). Explorando el uso de inteligencia artificial en el descubrimiento y diseño de microservicios. In Congresso Ibero-Americano em Engenharia de Software (CIbSE) - Doctoral Symposium, pages 224–231, Ciudad Real, Spain. SBC.
Narváez, D., Battaglia, N., Fernández, A., and Rossi, G. (2025a). Descubrimiento automático de microservicios mediante modelos generativos y verificación formal. In XXXI Congreso Argentino de Ciencias de la Computación (CACIC) (Viedma, 6 al 10 de octubre de 2025), Viedma, Argentina. Universidad Nacional de Río Negro (UNRN).
Narváez, D., Battaglia, N., Fernández, A., and Rossi, G. (2025b). Designing microservices using AI: A systematic literature review. Software, 4(1):6.
Narváez, D., Rossi, G., and Battaglia, N. (2024). Aplicación de inteligencia artificial en el diseño de microservicios. In XXX Congreso Argentino de Ciencias de la Computación (CACIC)(La Plata, 7 al 11 de octubre de 2024).
Neri, D., Soldani, J., Zimmermann, O., and Brogi, A. (2020). Design principles, architectural smells and refactorings for microservices: a multivocal review. SICS Software-Intensive Cyber-Physical Systems, 35(1):3–15.
Newman, S. (2021). Building microservices: designing fine-grained systems. ”O’Reilly Media, Inc.”.
Novikov, A., Vũ, N., Eisenberger, M., Dupont, E., Huang, P.-S., Wagner, A. Z., Shirobokov, S., Kozlovskii, B., Ruiz, F. J., Mehrabian, A., et al. (2025). Alphaevolve: A coding agent for scientific and algorithmic discovery. arXiv preprint arXiv:2506.13131.
Pereira, J. R. A., Albuquerque, D., Perkusich, M., Rodríguez, G., Díaz-Pace, J. A., Gorgônio, K., and Perkusich, A. (2025). Toward generating microservice architectures from textual requirements with large language models. In Simpósio Brasileiro de Componentes, Arquiteturas e Reutilização de Software (SBCARS), pages 79–89. SBC.
Pérez, G., Mostaccio, C., and Antonelli, L. (2025). Análisis comparativo de arquitecturas de nlp para detectar similitudes entre escenarios en español. In Workshop on Requirements Engineering (WER).
Taibi, D., Lenarduzzi, V., Pahl, C., and Janes, A. (2017). Microservices in agile software development: a workshop-based study into issues, advantages, and disadvantages. In Proceedings of the XP2017 Scientific Workshops, pages 1–5.
Taibi, D. and Systä, K. (2019). A decomposition and metric-based evaluation framework for microservices.
Ünlü, H., Kennouche, D. E., Soylu, G. K., and Demirörs, O. (2024). Microservice-based projects in agile world: A structured interview. Information and Software Technology, 165:107334.
Vera-Rivera, F. H., Cuadros, E. G. P., Perez, B., Astudillo, H., and Gaona, C. (2023). Semgromi—a semantic grouping algorithm to identifying microservices using semantic similarity of user stories. PeerJ Computer Science, 9:e1380.
Woods, E., Erder, M., and Pureur, P. (2021). Continuous architecture in practice: Software architecture in the age of agility and DevOps. Addison-Wesley Professional.
Publicado
11/05/2026
Como Citar
NARVÁEZ, Daniel; BATTAGLIA, Nicolás; FERNÁNDEZ, Alejandro; ROSSI, Gustavo.
ArchiGenMS: A Neuro-Symbolic Evolutionary Framework for Greenfield Microservice Design. In: CONGRESSO IBERO-AMERICANO EM ENGENHARIA DE SOFTWARE (CIBSE), 29. , 2026, Recife/PE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 365-372.
