Investigando a Integração Estrutural de LLMs em Ecossistemas de Software: Um Estudo com Modelagem SSN
Resumo
Ecossistemas de software (ECOS) são compostos por atores interconectados que colaboram na produção de software. A notação Software Supply Network (SSN) permite modelar estruturalmente esses ecossistemas, destacando as relações entre plataformas, ferramentas e agentes envolvidos. Com a crescente adoção de Modelos de Linguagem em Larga Escala (LLMs), como GitHub, Copilot e ChatGPT, novas dinâmicas emergem no desenvolvimento de código aberto, ainda pouco compreendidas de uma perspectiva estrutural. Este trabalho propõe uma análise preliminar do papel dos LLMs como agentes em quatro ecossistemas distintos — LangChain, VSCode, Transformers e Pandas — por meio da modelagem SSN e análise automatizada de Pull Requests. Os resultados revelam padrões contrastantes de centralidade dos LLMs, destacando seu potencial como elementos de reestruturação em redes de produção de software. A abordagem oferece uma nova lente para entender a inserção da IA em ECOS e levanta hipóteses relevantes para investigações futuras.
Referências
Vasilis Boucharas, Slinger Jansen, and Sjaak Brinkkemper. 2009. Formalizing Software Ecosystem Modeling (IWOCE ’09).
Gabriella Costa, Felyppe Silva, Rodrigo Santos, Cláudia Werner, and Toacy Oliveira. 2013. From Applications to a Software Ecosystem Platform: An Exploratory Study. In Proceedings of the Fifth International Conference on Management of Emergent Digital EcoSystems.
Carla Coutinho, Emanuel e Bezerra. 2020. A study on dynamic aspects variability in the SOLAR educational software ecosystem. Journal of the Brazilian Computer Society 26, 1 (2020), 1–19.
Emanuel F. Coutinho, Italo Santos, Leonardo O. Moreira, and Carla I. M. Bezerra. 2019. A Report on the Teaching of Software Ecosystems in Software Engineering Discipline. In Proceedings of the XXXIII Brazilian Symposium on Software Engineering (SBES 2019).
Emanuel Ferreira Coutinho, Davi Viana, and Rodrigo Pereira dos Santos. 2017. An Exploratory Study on the Need for Modeling Software Ecosystems: The Case of SOLAR SECO. In 9th InternationalWorkshop on Modelling in Software Engineering (MISE) (MISE ’17).
Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y. Wu, Y. K. Li, Fuli Luo, Yingfei Xiong, and Wenfeng Liang. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming – The Rise of Code Intelligence. arXiv:2401.14196 [cs.SE] [link]
Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, and Haoyu Wang. 2024. Large language models for software engineering: A systematic literature review. ACM Transactions on Software Engineering and Methodology 33, 8 (2024), 1–79.
Slinger Jansen. 2020. A focus area maturity model for software ecosystem governance. Information and Software Technology 118 (2020), 106219.
Slinger Jansen, Eko Handoyo, and Carina Alves. 2015. Scientists’ needs in modelling software ecosystems. In Proceedings of the 2015 European Conference on Software Architecture Workshops. 1–6.
Yacine Majdoub and Eya Ben Charrada. 2024. Debugging with Open-Source Large Language Models: An Evaluation. In Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM ’24). ACM, 510–516. DOI: 10.1145/3674805.3690758
Ipek Ozkaya. 2023. Application of large language models to software engineering tasks: Opportunities, risks, and implications. IEEE Software 40, 3 (2023), 4–8.
Francisco Pinheiro, Emanuel Coutinho, Ronier Lima, Maria Silva, Carla Bezerra, and Rossana Andrade. 2025. ECOS Modeling: A Modeling Tool, Repository for Models and Evolution Analysis of Software Ecosystems. In Anais do XXI Simpósio Brasileiro de Sistemas de Informação (Recife/PE). SBC, Porto Alegre, RS, Brasil, 369–378. DOI: 10.5753/sbsi.2025.246501
Francisco Victor Pinheiro, Emanuel Coutinho, Maria Erilane Silva, and Carla Bezerra. 2024. A Systematic Mapping of Health, Quality, Evolution, Simulation and Modeling in Software Ecosystems. In Proceedings of the 20th Brazilian Symposium on Information Systems (Juiz de Fora, Brazil) (SBSI ’24). Association for Computing Machinery, New York, NY, USA, Article 26, 10 pages. DOI: 10.1145/3658271.3658297
Francisco Victor da S. Pinheiro, Emanuel Ferreira Coutinho, Italo Santos, and Carla I. M. Bezerra. 2022. A Tool for Supporting the Teaching and Modeling of Software Ecosystems Using SSN Notation. Journal on Interactive Systems 13, 1 (Sep. 2022), 192–204. DOI: 10.5753/jis.2022.2602
Fangchen Song, Ashish Agarwal, and Wen Wen. 2024. The impact of generative AI on collaborative open-source software development: Evidence from GitHub Copilot. arXiv preprint arXiv:2410.02091 (2024).
Ivo van den Berk, Slinger Jansen, and Lútzen Luinenburg. 2010. Software Ecosystems: A Software Ecosystem Strategy Assessment Model. In Proceedings of the Fourth European Conference on Software Architecture: Companion Volume (Copenhagen, Denmark) (ECSA ’10). Association for Computing Machinery, New York, NY, USA, 127–134. DOI: 10.1145/1842752.1842781
Jelle Wouters, JR Ritmeester, AW Carlsen, Slinger Jansen, and Krzysztof Wnuk. 2019. A SECO meta-model. In International Conference on Software Business. Springer, 31–45.
Doron Yeverechyahu, Raveesh Mayya, and Gal Oestreicher-Singer. 2024. The impact of large language models on open-source innovation: Evidence from GitHub Copilot. arXiv preprint arXiv:2409.08379 (2024).
Zibin Zheng, Kaiwen Ning, Qingyuan Zhong, Jiachi Chen, Wenqing Chen, Lianghong Guo, Weicheng Wang, and Yanlin Wang. 2025. Towards an understanding of large language models in software engineering tasks. Empirical Software Engineering 30, 2 (2025), 50.
