Rumo a uma proposta de assistente estudantil na web descentralizada
Resumo
Na literatura há vários relatos de uso de agentes de IA no contexto educacional para proporcionar uma modernização de serviços. Neste artigo propõe-se o desenvolvimento de um assistente estudantil baseado em agentes inteligentes para operação em ambiente web descentralizada. O agente proposto faz uso de modelos de linguagem natural executados localmente e tem suas funcionalidades ampliadas por meio da integração dinâmica do agente com ferramentas externas disponíveis no contexto universitário por meio de interface padronizada. Por outro lado, a execução local garante o controle total sobre dados sensíveis dos estudantes, assegurando conformidade com a LGPD e proporcionando autonomia tecnológica às instituições educacionais. Testes experimentais utilizando a plataforma Hugging Face demonstraram capacidade satisfatória do agente em executar raciocínio estruturado e realizar chamadas de ferramentais externos ao modelo para prover respostas às consultas dos estudantes. Os resultados preliminares indicam viabilidade técnica da proposta, oferecendo uma alternativa às soluções centralizadas, baseadas em APIs cloud, para assistência acadêmica personalizada.
Palavras-chave:
Agentes Inteligentes, Assistente Estudantil, Privacidade de Dados
Referências
Brasil (2018). Lei geral de proteção de dados pessoais (lgpd) - lei nº 13.709.
Byron, L., Schrock, N., and Schafer, D. (2015). Graphql: A data query and manipulation language for apis. Facebook Engineering Blog.
Chen, W., Ma, X., Wang, X., and Cohen, W. W. (2022). Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv preprint arXiv:2211.12588.
Dolin, R. H., Alschuler, L., Boyer, S., Beebe, C., Behlen, F. M., Biron, P. V., and Shabo, A. (2006). Hl7 clinical document architecture, release 2. In Journal of the American Medical Informatics Association, volume 13, pages 30–39. BMJ Publishing Group.
Fire, M. M. and Guestrin, C. (2021). Interoperability standards in healthcare: A systematic review. IEEE Transactions on Biomedical Engineering, 68(8):2312–2322.
Han, J., Liu, G., and Gao, Y. (2023). Learners in the metaverse: A systematic review on the use of roblox in learning. Education Sciences, 13(3):296.
IMS Global Learning Consortium (2019). Learning tools interoperability (lti) version 1.3 and lti advantage. Technical report, IMS Global Learning Consortium.
JSON-RPC Working Group (2010). Json-rpc 2.0 specification. Technical report.
Lin, H., Wan, S., Gan, W., Chen, J., and Chao, H. C. (2022). Metaverse in education: Vision, opportunities, and challenges. In 2022 IEEE International Conference on Big Data (Big Data), pages 2857–2866. IEEE.
Lu, P., Peng, B., Cheng, H., Galley, M., Chang, K.-W., Wu, Y. N., Zhu, S.-C., and Gao, J. (2023). Chameleon: Plug-and-play compositional reasoning with large language models. arXiv preprint arXiv:2304.09842.
Mandel, J. C., Kreda, D. A., Mandl, K. D., Kohane, I. S., and Ramoni, R. B. (2016). Smart on fhir: a standards-based, interoperable apps platform for electronic health records. Journal of the American Medical Informatics Association, 23(5):899–908.
OpenAI, Anthropic, DeepMind, G., Research, M., et al. (2024). Model context protocol (mcp): An open protocol for tool integration with llms. arXiv preprint arXiv:2407.12590.
OpenAPI Initiative (2023). Openapi specification version 3.1.0. Technical report, Linux Foundation.
Parisi, A., Zhao, Y., and Fiedel, N. (2022). Talm: Tool augmented language models. In arXiv preprint arXiv:2205.12255.
Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., Zhao, S., Hong, L., Tian, R., Xie, R., Zhou, J., Gerstein, M., Li, D., Liu, Z., and Sun, M. (2023). Tool learning with foundation models. arXiv preprint arXiv:2304.08354.
Ruwodo, V., Pinomaa, A., Vesisenaho, M., Ntinda, M., and Sutinen, E. (2022). Enhancing software engineering education in africa through a metaversity. In 2022 IEEE Frontiers in Education Conference (FIE), pages 1–8. IEEE.
Schick, T., Dwivedi-Yu, J., Dessı̀, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., and Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761.
Wang, M., Yu, H., Bell, Z., and Chu, X. (2022). Constructing an edu-metaverse ecosystem: A new and innovative framework. IEEE Transactions on Learning Technologies, 15(6):685–696.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., and Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903.
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Scao, T. L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A. M. (2020). Transformers: State-of-the-art natural language processing. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45.
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2022). React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629.
Byron, L., Schrock, N., and Schafer, D. (2015). Graphql: A data query and manipulation language for apis. Facebook Engineering Blog.
Chen, W., Ma, X., Wang, X., and Cohen, W. W. (2022). Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. arXiv preprint arXiv:2211.12588.
Dolin, R. H., Alschuler, L., Boyer, S., Beebe, C., Behlen, F. M., Biron, P. V., and Shabo, A. (2006). Hl7 clinical document architecture, release 2. In Journal of the American Medical Informatics Association, volume 13, pages 30–39. BMJ Publishing Group.
Fire, M. M. and Guestrin, C. (2021). Interoperability standards in healthcare: A systematic review. IEEE Transactions on Biomedical Engineering, 68(8):2312–2322.
Han, J., Liu, G., and Gao, Y. (2023). Learners in the metaverse: A systematic review on the use of roblox in learning. Education Sciences, 13(3):296.
IMS Global Learning Consortium (2019). Learning tools interoperability (lti) version 1.3 and lti advantage. Technical report, IMS Global Learning Consortium.
JSON-RPC Working Group (2010). Json-rpc 2.0 specification. Technical report.
Lin, H., Wan, S., Gan, W., Chen, J., and Chao, H. C. (2022). Metaverse in education: Vision, opportunities, and challenges. In 2022 IEEE International Conference on Big Data (Big Data), pages 2857–2866. IEEE.
Lu, P., Peng, B., Cheng, H., Galley, M., Chang, K.-W., Wu, Y. N., Zhu, S.-C., and Gao, J. (2023). Chameleon: Plug-and-play compositional reasoning with large language models. arXiv preprint arXiv:2304.09842.
Mandel, J. C., Kreda, D. A., Mandl, K. D., Kohane, I. S., and Ramoni, R. B. (2016). Smart on fhir: a standards-based, interoperable apps platform for electronic health records. Journal of the American Medical Informatics Association, 23(5):899–908.
OpenAI, Anthropic, DeepMind, G., Research, M., et al. (2024). Model context protocol (mcp): An open protocol for tool integration with llms. arXiv preprint arXiv:2407.12590.
OpenAPI Initiative (2023). Openapi specification version 3.1.0. Technical report, Linux Foundation.
Parisi, A., Zhao, Y., and Fiedel, N. (2022). Talm: Tool augmented language models. In arXiv preprint arXiv:2205.12255.
Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., Zhao, S., Hong, L., Tian, R., Xie, R., Zhou, J., Gerstein, M., Li, D., Liu, Z., and Sun, M. (2023). Tool learning with foundation models. arXiv preprint arXiv:2304.08354.
Ruwodo, V., Pinomaa, A., Vesisenaho, M., Ntinda, M., and Sutinen, E. (2022). Enhancing software engineering education in africa through a metaversity. In 2022 IEEE Frontiers in Education Conference (FIE), pages 1–8. IEEE.
Schick, T., Dwivedi-Yu, J., Dessı̀, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., and Scialom, T. (2023). Toolformer: Language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761.
Wang, M., Yu, H., Bell, Z., and Chu, X. (2022). Constructing an edu-metaverse ecosystem: A new and innovative framework. IEEE Transactions on Learning Technologies, 15(6):685–696.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., and Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903.
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Scao, T. L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A. M. (2020). Transformers: State-of-the-art natural language processing. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45.
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2022). React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629.
Publicado
24/11/2025
Como Citar
CARVALHO, Deivid Alves de; CRUZ, Fernando Willian.
Rumo a uma proposta de assistente estudantil na web descentralizada. In: WORKSHOP SOBRE DESCENTRALIZAÇÃO EM INFORMÁTICA NA EDUCAÇÃO (WDESCENTRAIE), 1. , 2025, Curitiba/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 14-21.
DOI: https://doi.org/10.5753/wdescentraie.2025.15941.
