OPTIFETCH: Um Agente de Prefetching Probabilístico para Apoiar a Experiência de Aprendizagem em Sistemas Tutores Inteligentes sob Conectividade Instável
Resumo
Sistemas Tutores Inteligentes baseados em modelos de linguagem remotos podem apresentar alta latência sob conectividade instável. Este trabalho apresenta o OPTIFETCH, um agente de prefetching que utiliza a probabilidade de erro estimada pelo Bayesian Knowledge Tracing para antecipar dicas. A proposta foi avaliada por simulações controladas em cenários Wi-Fi, 4G e rural, em comparação com as estratégias On-Demand e Prefetching Agressivo. Nas condições simuladas, o OPTIFETCH reduziu a latência percebida entre 35,3% e 44,4% frente ao On-Demand e apresentou menor custo agregado que as duas referências. Os resultados indicam viabilidade operacional, mas não evidenciam impacto sobre a aprendizagem.
Palavras-chave:
Sistemas Tutores Inteligentes, Prefetching, Conectividade Instável
Referências
Baker, R. S. J. d., Corbett, A. T., and Aleven, V. (2008). More accurate student modeling through contextual estimation of slip and guess probabilities in bayesian knowledge tracing. In Woolf, B. P., Aïmeur, E., Nkambou, R., and Lajoie, S., editors, Intelligent Tutoring Systems, pages 406–415, Berlin, Heidelberg. Springer Berlin Heidelberg.
Corbett, A. T. and Anderson, J. R. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4(4):253–278.
Dakshit, S. (2024). Faculty perspectives on the potential of rag in computer science higher education.
Granata, F., Poggi, F., and Mongiovì, M. (2025). Enhancing retrieval-augmented generation with entity linking for educational platforms.
Harmon, K. A., Lee, H., Khasraghi, B. J., Parmar, H. S., and Walden, E. A. (2024). Delays in information presentation lead to brain state switching, which degrades user performance, and there may not be much we can do about it. MIS Quarterly, 48(1):273–298.
Isotani, S., Bittencourt, I. I., Challco, G. C., Dermeval, D., and Mello, R. F. (2023). Aied unplugged: Leapfrogging the digital divide to reach the underserved. In Wang, N., Rebolledo-Mendez, G., Dimitrova, V., Matsuda, N., and Santos, O. C., editors, Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky, pages 772–779, Cham. Springer Nature Switzerland.
Ko, S.-W., Huang, K., Kim, S.-L., and Chae, H. (2017). Live prefetching for mobile computation offloading. IEEE Transactions on Wireless Communications, 16(5):3057–3071.
Li, Z., Wang, Z., Wang, W., Hung, K., Xie, H., and Wang, F. L. (2025). Retrieval-augmented generation for educational application: A systematic survey. Computers and Education: Artificial Intelligence, 8:100417.
Pavlik, P. I., Cen, H., and Koedinger, K. R. (2009). Performance factors analysis – a new alternative to knowledge tracing. In Proceedings of the 14th International Conference on Artificial Intelligence in Education (AIED), pages 531–538.
Pelánek, R. (2017). Bayesian knowledge tracing, logistic models, and beyond: an overview of learner modeling techniques. User Modeling and User-Adapted Interaction, 27(3):313–350.
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., and Sohl-Dickstein, J. (2015). Deep knowledge tracing. In Advances in Neural Information Processing Systems (NeurIPS), volume 28.
Rodrigues, L., Guerino, G., Challco, G., Veloso, T., Oliveira, L., Penha, R., Melo, R., Vieira, T., Marinho, M., Macario, V., Bittencourt, I., Isotani, S., and Dermeval, D. (2023). Teacher-centered intelligent tutoring systems: Design considerations from brazilian, public school teachers. In Anais do XXXIV Simpósio Brasileiro de Informática na Educação, pages 1419–1430, Porto Alegre, RS, Brasil. SBC.
Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1):30–39.
Seow, S. C. (2008). Designing and Engineering Time: The Psychology of Time Perception in Software. Addison-Wesley Professional.
Siris, V., Anagnostopoulou, M., and Dimopoulos, D. (2014). Improving mobile video streaming with mobility prediction and prefetching in integrated cellular-wifi networks.
Swacha, J. and Gracel, M. (2025). Retrieval-augmented generation (rag) chatbots for education: A survey of applications. Applied Sciences, 15(8).
Tolia, N., Andersen, D. G., and Satyanarayanan, M. (2006). Quantifying interactive user experience on thin clients. Computer, 39(3):46–52.
Van Damme, S., Sameri, M. J., Schwarzmann, S., Wei, Q., Trivisonno, R., De Turck, F., and Torres Vega, M. (2024). Impact of latency on qoe, performance, and collaboration in interactive multi-user virtual reality. Applied Sciences, 14(6):2290.
VanLehn, K. (2006). The behavior of tutoring systems. International Journal of Artificial Intelligence in Education, 16(3):227–265.
Zhao, W., Ge, Y., Qu, W., Zhang, K., and Sun, X. (2017). The duration perception of loading applications in smartphone: Effects of different loading types. Applied Ergonomics, 65:223–232.
Zhao, Y., Laser, M. S., Lyu, Y., and Medvidovic, N. (2018a). Leveraging program analysis to reduce user-perceived latency in mobile applications. In Proceedings of the 40th International Conference on Software Engineering, ICSE '18, page 176–186. ACM.
Zhao, Y., Wat, P., Laser, M. S., and Medvidović, N. (2018b). Empirically assessing opportunities for prefetching and caching in mobile apps. In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, ASE '18, page 554–564. ACM.
Corbett, A. T. and Anderson, J. R. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4(4):253–278.
Dakshit, S. (2024). Faculty perspectives on the potential of rag in computer science higher education.
Granata, F., Poggi, F., and Mongiovì, M. (2025). Enhancing retrieval-augmented generation with entity linking for educational platforms.
Harmon, K. A., Lee, H., Khasraghi, B. J., Parmar, H. S., and Walden, E. A. (2024). Delays in information presentation lead to brain state switching, which degrades user performance, and there may not be much we can do about it. MIS Quarterly, 48(1):273–298.
Isotani, S., Bittencourt, I. I., Challco, G. C., Dermeval, D., and Mello, R. F. (2023). Aied unplugged: Leapfrogging the digital divide to reach the underserved. In Wang, N., Rebolledo-Mendez, G., Dimitrova, V., Matsuda, N., and Santos, O. C., editors, Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky, pages 772–779, Cham. Springer Nature Switzerland.
Ko, S.-W., Huang, K., Kim, S.-L., and Chae, H. (2017). Live prefetching for mobile computation offloading. IEEE Transactions on Wireless Communications, 16(5):3057–3071.
Li, Z., Wang, Z., Wang, W., Hung, K., Xie, H., and Wang, F. L. (2025). Retrieval-augmented generation for educational application: A systematic survey. Computers and Education: Artificial Intelligence, 8:100417.
Pavlik, P. I., Cen, H., and Koedinger, K. R. (2009). Performance factors analysis – a new alternative to knowledge tracing. In Proceedings of the 14th International Conference on Artificial Intelligence in Education (AIED), pages 531–538.
Pelánek, R. (2017). Bayesian knowledge tracing, logistic models, and beyond: an overview of learner modeling techniques. User Modeling and User-Adapted Interaction, 27(3):313–350.
Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., and Sohl-Dickstein, J. (2015). Deep knowledge tracing. In Advances in Neural Information Processing Systems (NeurIPS), volume 28.
Rodrigues, L., Guerino, G., Challco, G., Veloso, T., Oliveira, L., Penha, R., Melo, R., Vieira, T., Marinho, M., Macario, V., Bittencourt, I., Isotani, S., and Dermeval, D. (2023). Teacher-centered intelligent tutoring systems: Design considerations from brazilian, public school teachers. In Anais do XXXIV Simpósio Brasileiro de Informática na Educação, pages 1419–1430, Porto Alegre, RS, Brasil. SBC.
Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1):30–39.
Seow, S. C. (2008). Designing and Engineering Time: The Psychology of Time Perception in Software. Addison-Wesley Professional.
Siris, V., Anagnostopoulou, M., and Dimopoulos, D. (2014). Improving mobile video streaming with mobility prediction and prefetching in integrated cellular-wifi networks.
Swacha, J. and Gracel, M. (2025). Retrieval-augmented generation (rag) chatbots for education: A survey of applications. Applied Sciences, 15(8).
Tolia, N., Andersen, D. G., and Satyanarayanan, M. (2006). Quantifying interactive user experience on thin clients. Computer, 39(3):46–52.
Van Damme, S., Sameri, M. J., Schwarzmann, S., Wei, Q., Trivisonno, R., De Turck, F., and Torres Vega, M. (2024). Impact of latency on qoe, performance, and collaboration in interactive multi-user virtual reality. Applied Sciences, 14(6):2290.
VanLehn, K. (2006). The behavior of tutoring systems. International Journal of Artificial Intelligence in Education, 16(3):227–265.
Zhao, W., Ge, Y., Qu, W., Zhang, K., and Sun, X. (2017). The duration perception of loading applications in smartphone: Effects of different loading types. Applied Ergonomics, 65:223–232.
Zhao, Y., Laser, M. S., Lyu, Y., and Medvidovic, N. (2018a). Leveraging program analysis to reduce user-perceived latency in mobile applications. In Proceedings of the 40th International Conference on Software Engineering, ICSE '18, page 176–186. ACM.
Zhao, Y., Wat, P., Laser, M. S., and Medvidović, N. (2018b). Empirically assessing opportunities for prefetching and caching in mobile apps. In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, ASE '18, page 554–564. ACM.
Publicado
05/10/2026
Como Citar
DO AMARAL, Alex Almeida; QUEIROZ, João Carlos Herculano da Silva; DA SILVA, Huliane Medeiros; CHALLCO, Geiser Chalco.
OPTIFETCH: Um Agente de Prefetching Probabilístico para Apoiar a Experiência de Aprendizagem em Sistemas Tutores Inteligentes sob Conectividade Instável. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 774-788.
DOI: https://doi.org/10.5753/sbie.2026.27298.
