Avaliação do uso de LLMs para Suporte à Tomada de Decisão na Adoção de Padrões de Projeto em Software Orientado a Objetos
Resumo
Padrões de projeto são soluções reutilizáveis aplicadas a problemas recorrentes no desenvolvimento de software, visando melhorar a qualidade do projeto. O uso de tais padrões pode trazer uma série de benefícios à arquitetura do software a ser desenvolvido; entretanto, dada a variedade de padrões existentes e seus diferentes propósitos, projetistas inexperientes podem ter dificuldade em identificar padrões apropriados ao contexto. Este trabalho investiga o potencial do uso de grandes modelos de linguagem (LLM, do inglês, Large Language Model) na assistência a projetistas no emprego de padrões de projeto em aplicações desenvolvidas sob o paradigma da orientação a objetos. A principal questão discutida e avaliada no artigo é se ferramentas baseadas em LLMs conseguem sugerir e orientar projetistas na escolha e aplicação de padrões em etapas iniciais do projeto. Experimentos foram realizados usando diferentes ferramentas e os resultados foram discutidos e comparados, destacando seus potenciais para apoiar o projeto de arquiteturas de software.
Palavras-chave:
inteligência artificial, grandes modelos de linguagem, LLM, engenharia de software, padrões de projeto, arquitetura de software
Referências
Charu C. Aggarwal. 2023. Neural Networks and Deep Learning: A Textbook (2nd ed.). Springer Publishing Company, Incorporated.
Christopher Alexander, Sara Ishikawa, and Murray Silverstein. 1977. A Pattern Language: Towns, Buildings, Construction. Oxford University Press, New York, USA. 1216 pages.
Amazon Web Services. 2025. Amazon Q Developer. [link]
Anthropic. 2024. Claude 3.5 Sonnet Model Card Addendum. Technical Report. Anthropic.
Anysphere Inc. 2025. Cursor. [link]
Jameleh Asaad and Elena Avksentieva. 2025. Assessing the Impact of Gof Design Patterns on Software Engineering Practices. In 2025 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM). 930–934. DOI: 10.1109/ICIEAM65163.2025.11028537
B. Bafandeh Mayvan, A. Rasoolzadegan, and Z. Ghavidel Yazdi. 2017. The state of the art on design patterns: A systematic mapping of the literature. Journal of Systems and Software 125 (2017), 93–118. DOI: 10.1016/j.jss.2016.11.030
Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023).
Arifa I. Champa, Md Fazle Rabbi, Costain Nachuma, and Minhaz F. Zibran. 2024. ChatGPT in Action: Analyzing Its Use in Software Development. In 2024 IEEE/ACM 21st International Conference on Mining Software Repositories (MSR). 182–186.
Hai Dang, Ben Lafreniere, Tovi Grossman, Kashyap Todi, and Michelle Li. 2025. Authoring LLM-Based Assistance for Real-World Contexts and Tasks. In Proceedings of the 30th International Conference on Intelligent User Interfaces (IUI ’25). Association for Computing Machinery, New York, NY, USA, 211–230. DOI: 10.1145/3708359.3712164
DeepSeek AI. 2025. DeepSeek. [link]
Rushali Deshmukh, Rutuj Raut, Mayur Bhavsar, Sanika Gurav, and Yash Patil. 2025. Optimizing Human-AI Interaction: Innovations in Prompt Engineering. In 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT). 1240–1246. DOI: 10.1109/IDCIOT64235.2025.10914815
Hao Ding, Ziwei Fan, Ingo Guehring, Gaurav Gupta, Wooseok Ha, Jun Huan, Linbo Liu, Behrooz Omidvar-Tehrani, ShiqiWang, and Hao Zhou. 2024. Reasoning and Planning with Large Language Models in Code Development. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Barcelona, Spain) (KDD ’24). Association for Computing Machinery, New York, NY, USA, 6480–6490. DOI: 10.1145/3637528.3671452
Willian Freire, Murilo Boccardo, Daniel Nouchi, Aline Amaral, Silvia Vergilio, Thiago Ferreira, and Thelma Colanzi. 2024. Large Language Model-based suggestion of objective functions for search-based Product Line Architecture design. In Anais do XVIII Simpósio Brasileiro de Componentes, Arquiteturas e Reutilização de Software (Curitiba/PR). SBC, Porto Alegre, RS, Brasil, 21–30. DOI: 10.5753/sbcars.2024.3833
Erich Gamma. 1995. Design patterns: elements of reusable object-oriented software. Pearson Education India.
Erich Gamma. 2011. Design patterns—ten years later. Software pioneers: contributions to software engineering (2011), 688–700.
Github/OpenAI. 2022. Github Copilot. Retrieved July 6, 2025 from [link]
Google DeepMind. 2023. Gemini. [link]
Jasmin Jahić and Ashkan Sami. 2024. State of Practice: LLMs in Software Engineering and Software Architecture. In 2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C). 311–318. DOI: 10.1109/ICSAC63560.2024.00059
Hamraz Javaheri, Omid Ghamarnejad, Paul Lukowicz, Gregor Alexander Stavrou, and Jakob Karolus. 2024. ARAS: LLM-Supported Augmented Reality Assistance System for Pancreatic Surgery. In Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing (Melbourne VIC, Australia) (UbiComp ’24). Association for Computing Machinery, New York, NY, USA, 176–180. DOI: 10.1145/3675094.3677543
Marcos Kalinowski. 2008. Introdução à inspeção de software. Revista Engenharia de Software: Qualidade de software 1 (2008), 68–74.
Sascha Kaltenpoth and Oliver Müller. 2025. Don’t Touch the Power Line - A Proof-of-Concept for Aligned LLM-Based Assistance Systems to Support the Maintenance in the Electricity Distribution System. SIGENERGY Energy Inform. Rev. 4, 4 (Feb. 2025), 16–22. DOI: 10.1145/3717413.3717415
Rui Mao, Guanyi Chen, Xulang Zhang, Frank Guerin, and Erik Cambria. 2023. GPTEval: A survey on assessments of ChatGPT and GPT-4. arXiv preprint arXiv:2308.12488 (2023).
Ggaliwango Marvin, Nakayiza Hellen, Daudi Jjingo, and Joyce Nakatumba-Nabende. 2024. Prompt Engineering in Large Language Models. In Data Intelligence and Cognitive Informatics, I. Jeena Jacob, Selwyn Piramuthu, and Przemyslaw Falkowski-Gilski (Eds.). Springer Nature Singapore, Singapore, 387–402.
Timothy R McIntosh, Teo Susnjak, Tong Liu, Paul Watters, and Malka N Halgamuge. 2023. From google gemini to openai q*(q-star): A survey of reshaping the generative artificial intelligence (ai) research landscape. arXiv preprint arXiv:2312.10868 (2023).
Monica (Butterfly Effect AI). 2025. Manus AI. [link]
Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian. 2025. A Comprehensive Overview of Large Language Models. ACM Trans. Intell. Syst. Technol. (June 2025). DOI: 10.1145/3744746 Just Accepted.
Fnu Neha and Deepshikha Bhati. 2025. A Survey of DeepSeek Models. Authorea Preprints (2025).
OpenAI. 2023. ChatGPT. [link]
Zhenyu Pan, Xuefeng Song, Yunkun Wang, Rongyu Cao, Binhua Li, Yongbin Li, and Han Liu. 2025. Do Code LLMs Understand Design Patterns? arXiv:2501.04835 [cs.SE] [link]
Sushant Kumar Pandey, Sivajeet Chand, Jennifer Horkoff, Miroslaw Staron, Miroslaw Ochodek, and Darko Durisic. 2025. Design pattern recognition: a study of large language models. Empirical Software Engineering 30, 3 (2025), 69.
Larissa Schmid, Tobias Hey, Martin Armbruster, Sophie Corallo, Dominik Fuchß, Jan Keim, Haoyu Liu, and Anne Koziolek. 2025. Software Architecture Meets LLMs: A Systematic Literature Review. arXiv:2505.16697 [cs.SE] [link]
Minjie Shen and Qikai Yang. 2025. From mind to machine: The rise of manus ai as a fully autonomous digital agent. arXiv preprint arXiv:2505.02024 (2025).
Siqi Shen, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Soujanya Poria, and Rada Mihalcea. 2024. Understanding the capabilities and limitations of large language models for cultural commonsense. arXiv preprint arXiv:2405.04655 (2024).
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).
Jules White, Sam Hays, Quchen Fu, Jesse Spencer-Smith, and Douglas C. Schmidt. 2024. ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design. Springer Nature Switzerland, Cham, 71–108. DOI: 10.1007/978-3-031-55642-5_4
Zihao Yi, Jiarui Ouyang, Yuwen Liu, Tianhao Liao, Zhe Xu, and Ying Shen. 2024. A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems. arXiv:2402.18013 [cs.CL] [link]
Quanjun Zhang, Chunrong Fang, Yang Xie, Yaxin Zhang, Yun Yang,Weisong Sun, Shengcheng Yu, and Zhenyu Chen. 2024. A Survey on Large Language Models for Software Engineering. arXiv:2312.15223 [cs.SE] [link]
Xun Zhang, Hironori Washizaki, Nobukazu Yoshioka, and Yoshiaki Fukazawa. 2022. Detecting Design Patterns in UML Class Diagram Images using Deep Learning. In 2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD). 27–32. DOI: 10.1109/SNPD54884.2022.10051795
Christopher Alexander, Sara Ishikawa, and Murray Silverstein. 1977. A Pattern Language: Towns, Buildings, Construction. Oxford University Press, New York, USA. 1216 pages.
Amazon Web Services. 2025. Amazon Q Developer. [link]
Anthropic. 2024. Claude 3.5 Sonnet Model Card Addendum. Technical Report. Anthropic.
Anysphere Inc. 2025. Cursor. [link]
Jameleh Asaad and Elena Avksentieva. 2025. Assessing the Impact of Gof Design Patterns on Software Engineering Practices. In 2025 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM). 930–934. DOI: 10.1109/ICIEAM65163.2025.11028537
B. Bafandeh Mayvan, A. Rasoolzadegan, and Z. Ghavidel Yazdi. 2017. The state of the art on design patterns: A systematic mapping of the literature. Journal of Systems and Software 125 (2017), 93–118. DOI: 10.1016/j.jss.2016.11.030
Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023).
Arifa I. Champa, Md Fazle Rabbi, Costain Nachuma, and Minhaz F. Zibran. 2024. ChatGPT in Action: Analyzing Its Use in Software Development. In 2024 IEEE/ACM 21st International Conference on Mining Software Repositories (MSR). 182–186.
Hai Dang, Ben Lafreniere, Tovi Grossman, Kashyap Todi, and Michelle Li. 2025. Authoring LLM-Based Assistance for Real-World Contexts and Tasks. In Proceedings of the 30th International Conference on Intelligent User Interfaces (IUI ’25). Association for Computing Machinery, New York, NY, USA, 211–230. DOI: 10.1145/3708359.3712164
DeepSeek AI. 2025. DeepSeek. [link]
Rushali Deshmukh, Rutuj Raut, Mayur Bhavsar, Sanika Gurav, and Yash Patil. 2025. Optimizing Human-AI Interaction: Innovations in Prompt Engineering. In 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT). 1240–1246. DOI: 10.1109/IDCIOT64235.2025.10914815
Hao Ding, Ziwei Fan, Ingo Guehring, Gaurav Gupta, Wooseok Ha, Jun Huan, Linbo Liu, Behrooz Omidvar-Tehrani, ShiqiWang, and Hao Zhou. 2024. Reasoning and Planning with Large Language Models in Code Development. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Barcelona, Spain) (KDD ’24). Association for Computing Machinery, New York, NY, USA, 6480–6490. DOI: 10.1145/3637528.3671452
Willian Freire, Murilo Boccardo, Daniel Nouchi, Aline Amaral, Silvia Vergilio, Thiago Ferreira, and Thelma Colanzi. 2024. Large Language Model-based suggestion of objective functions for search-based Product Line Architecture design. In Anais do XVIII Simpósio Brasileiro de Componentes, Arquiteturas e Reutilização de Software (Curitiba/PR). SBC, Porto Alegre, RS, Brasil, 21–30. DOI: 10.5753/sbcars.2024.3833
Erich Gamma. 1995. Design patterns: elements of reusable object-oriented software. Pearson Education India.
Erich Gamma. 2011. Design patterns—ten years later. Software pioneers: contributions to software engineering (2011), 688–700.
Github/OpenAI. 2022. Github Copilot. Retrieved July 6, 2025 from [link]
Google DeepMind. 2023. Gemini. [link]
Jasmin Jahić and Ashkan Sami. 2024. State of Practice: LLMs in Software Engineering and Software Architecture. In 2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C). 311–318. DOI: 10.1109/ICSAC63560.2024.00059
Hamraz Javaheri, Omid Ghamarnejad, Paul Lukowicz, Gregor Alexander Stavrou, and Jakob Karolus. 2024. ARAS: LLM-Supported Augmented Reality Assistance System for Pancreatic Surgery. In Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing (Melbourne VIC, Australia) (UbiComp ’24). Association for Computing Machinery, New York, NY, USA, 176–180. DOI: 10.1145/3675094.3677543
Marcos Kalinowski. 2008. Introdução à inspeção de software. Revista Engenharia de Software: Qualidade de software 1 (2008), 68–74.
Sascha Kaltenpoth and Oliver Müller. 2025. Don’t Touch the Power Line - A Proof-of-Concept for Aligned LLM-Based Assistance Systems to Support the Maintenance in the Electricity Distribution System. SIGENERGY Energy Inform. Rev. 4, 4 (Feb. 2025), 16–22. DOI: 10.1145/3717413.3717415
Rui Mao, Guanyi Chen, Xulang Zhang, Frank Guerin, and Erik Cambria. 2023. GPTEval: A survey on assessments of ChatGPT and GPT-4. arXiv preprint arXiv:2308.12488 (2023).
Ggaliwango Marvin, Nakayiza Hellen, Daudi Jjingo, and Joyce Nakatumba-Nabende. 2024. Prompt Engineering in Large Language Models. In Data Intelligence and Cognitive Informatics, I. Jeena Jacob, Selwyn Piramuthu, and Przemyslaw Falkowski-Gilski (Eds.). Springer Nature Singapore, Singapore, 387–402.
Timothy R McIntosh, Teo Susnjak, Tong Liu, Paul Watters, and Malka N Halgamuge. 2023. From google gemini to openai q*(q-star): A survey of reshaping the generative artificial intelligence (ai) research landscape. arXiv preprint arXiv:2312.10868 (2023).
Monica (Butterfly Effect AI). 2025. Manus AI. [link]
Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian. 2025. A Comprehensive Overview of Large Language Models. ACM Trans. Intell. Syst. Technol. (June 2025). DOI: 10.1145/3744746 Just Accepted.
Fnu Neha and Deepshikha Bhati. 2025. A Survey of DeepSeek Models. Authorea Preprints (2025).
OpenAI. 2023. ChatGPT. [link]
Zhenyu Pan, Xuefeng Song, Yunkun Wang, Rongyu Cao, Binhua Li, Yongbin Li, and Han Liu. 2025. Do Code LLMs Understand Design Patterns? arXiv:2501.04835 [cs.SE] [link]
Sushant Kumar Pandey, Sivajeet Chand, Jennifer Horkoff, Miroslaw Staron, Miroslaw Ochodek, and Darko Durisic. 2025. Design pattern recognition: a study of large language models. Empirical Software Engineering 30, 3 (2025), 69.
Larissa Schmid, Tobias Hey, Martin Armbruster, Sophie Corallo, Dominik Fuchß, Jan Keim, Haoyu Liu, and Anne Koziolek. 2025. Software Architecture Meets LLMs: A Systematic Literature Review. arXiv:2505.16697 [cs.SE] [link]
Minjie Shen and Qikai Yang. 2025. From mind to machine: The rise of manus ai as a fully autonomous digital agent. arXiv preprint arXiv:2505.02024 (2025).
Siqi Shen, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Soujanya Poria, and Rada Mihalcea. 2024. Understanding the capabilities and limitations of large language models for cultural commonsense. arXiv preprint arXiv:2405.04655 (2024).
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).
Jules White, Sam Hays, Quchen Fu, Jesse Spencer-Smith, and Douglas C. Schmidt. 2024. ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design. Springer Nature Switzerland, Cham, 71–108. DOI: 10.1007/978-3-031-55642-5_4
Zihao Yi, Jiarui Ouyang, Yuwen Liu, Tianhao Liao, Zhe Xu, and Ying Shen. 2024. A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems. arXiv:2402.18013 [cs.CL] [link]
Quanjun Zhang, Chunrong Fang, Yang Xie, Yaxin Zhang, Yun Yang,Weisong Sun, Shengcheng Yu, and Zhenyu Chen. 2024. A Survey on Large Language Models for Software Engineering. arXiv:2312.15223 [cs.SE] [link]
Xun Zhang, Hironori Washizaki, Nobukazu Yoshioka, and Yoshiaki Fukazawa. 2022. Detecting Design Patterns in UML Class Diagram Images using Deep Learning. In 2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD). 27–32. DOI: 10.1109/SNPD54884.2022.10051795
Publicado
22/09/2025
Como Citar
COLOMBO, Vitor Monteiro; SOUZA, Weslen Schiavon de; BRISOLARA, Lisane Brisolara de; SANTANA, Brenda Salenave; TAVARES, Tatiana Aires.
Avaliação do uso de LLMs para Suporte à Tomada de Decisão na Adoção de Padrões de Projeto em Software Orientado a Objetos. In: SIMPÓSIO BRASILEIRO DE COMPONENTES, ARQUITETURAS E REUTILIZAÇÃO DE SOFTWARE (SBCARS), 19. , 2025, Recife/PE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 101-111.
DOI: https://doi.org/10.5753/sbcars.2025.14602.
