Desarrollo y Evaluación de un Tutor Inteligente para el aprendizaje de programación basado en los Modelos de Lenguaje Extenso
Resumo
El comportamiento emergente de la programación automática tras la popularización de la Inteligencia Artificial Generativa ha generado incertidumbre sobre el futuro de la programación y su enseñanza. Este trabajo doctoral propone diseñar y evaluar una arquitectura para el desarrollo de Sistemas de Tutoría Inteligente para el aprendizaje de programación que integran Modelos de Lenguaje Extenso para ofrecer una experiencia de usuario personalizada. La arquitectura se desarrolla con una metodología de investigación basada en diseño, evaluándose su efecto en el compromiso cognitivo y el aprendizaje mediante pruebas formativas del prototipo y una evaluación sumativa a través de un estudio de intervención.
Palavras-chave:
Ingeniería de Software, Modelos de Lenguaje Extenso, Sistemas de Tutoría Inteligente, Inteligencia Artificial Generativa, Aprendizaje de programación, Personalización del aprendizaje
Referências
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S.,... & Liang, P. (2021). “On the opportunities and risks of foundation models”. arXiv preprint. DOI: 10.48550/arXiv.2108.07258
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P.,... & Amodei, D. (2020). “Language models are few-shot learners”. Advances in neural information processing systems, 33, 1877-1901. DOI: 10.48550/arXiv.2005.14165
Denny, P., Prather, J., Becker, B. A., Finnie-Ansley, J., Hellas, A., Leinonen, J.,... & Sarsa, S. (2024). “Computing education in the era of generative AI”. Communications of the ACM, 67(2), 56-67. DOI: 10.1145/3624720
Du Plooy, E., Casteleijn, D., & Franzsen, D. (2024). “Personalized adaptive learning in higher education: a scoping review of key characteristics and impact on academic performance and engagement”. Heliyon, 10(21), e39630. DOI: 10.1016/j.heliyon.2024.e39630
Fernández, L. R., Mena, A. L. F., Magaña, M. P. T., Magaña, M. A. R., & Fernández, M. A. R. (2024). “Inteligencia artificial en la educación: Modelo de lenguaje de gran tamaño (LLM) como recurso educativo”. Revista IPSUMTEC, 7(2), 157-164. DOI: 10.61117/ipsumtec.v7i2.321
Gao, L., Lu, J., Shao, Z., Lin, Z., Yue, S., Ieong, C.,... & Chen, S. (2024). “Fine-tuned large language model for visualization system: A study on self-regulated learning in education”. IEEE Transactions on Visualization and Computer Graphics. DOI: 10.1109/TVCG.2024.3456145
Goodfellow, I., Bengio, Y., & Courville, A. (2016). “Deep learning”. MIT Press.
Halverson, L. R., & Graham, C. R. (2019). “Learner Engagement in Blended Learning Environments: A Conceptual Framework”. Online Learning, 23, 145-178. DOI: 10.24059/olj.v23i2.1481
Johannesson, P., & Perjons, E. (2021). “An Introduction to Design Science”. In Springer eBooks. DOI: 10.1007/978-3-030-78132-3
Khan, H., Gul, R., & Zeb, M. (2023). “The Effect of Students’ Cognitive and Emotional Engagement on Students’ Academic Success and Academic Productivity”. Journal Of Social Sciences Review, 3(1), 322-334. DOI: 10.54183/jssr.v3i1.141
Lange, C. (2021). “The relationship between e-learning personalization and cognitive load”. Open Learning the Journal of Open Distance And e-Learning, 38(3), 228-242. DOI: 10.1080/02680513.2021.2019577
Levchuk, O. (2024). Diseño y evaluación de un tutor inteligente basado en Inteligencia Artificial Generativa para la adquisición de habilidades de programación. Tesis de Maestría en Ciencias. CICESE, Baja California, México. 92 pp.
Levchuk, O., Sánchez, C., Pacheco, N., López, I., & Favela, J. (2024). “Interaction Design (IxD) of an Intelligent Tutor for Programming Learning Based on LLM”. Avances en Interacción Humano-Computadora, 9(1), 1–10. DOI: 10.47756/aihc.y9i1.137
Liu, Z., He, X., Liu, L., Liu, T., & Zhai, X. (2023). “Context matters: A strategy to pre-train language model for science education”. In International Conference on Artificial Intelligence in Education, 666-674. Cham: Springer Nature Switzerland. DOI: 10.1007/978-3-031-36336-8_103
Qureshi, B. (2023). “Exploring the use of chatgpt as a tool for learning and assessment in undergraduate computer science curriculum: Opportunities and challenges”. ArXiv preprint. DOI: 10.48550/arXiv.2304.11214
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D. & Sutskever, I. (2019). “Language Models are Unsupervised Multitask Learners”. OpenAI.
Rahman, M. M., & Watanobe, Y. (2023). “ChatGPT for Education and Research: Opportunities, Threats, and Strategies”. Applied Sciences, 13(9), 5783. DOI: 10.3390/app13095783
Scherer, R., Siddiq, F., & Viveros, B. S. (2020). “A meta-analysis of teaching and learning computer programming: Effective instructional approaches and conditions”. Computers In Human Behavior, 109, 106349. DOI: 10.1016/j.chb.2020.106349
Schmucker, R., Xia, M., Azaria, A., & Mitchell, T. (2023). “Ruffle&riley: Towards the automated induction of conversational tutoring systems”. ArXiv preprint. DOI: 10.48550/arXiv.2310.01420
Singh, D., & Rajendran, R. (2024). “Cognitive engagement as a predictor of learning gain in Python programming”. Smart Learning Environments, 11(1). DOI: 10.1186/s40561-024-00330-9
Sonkar, S., Ni, K., Chaudhary, S., & Baraniuk, R. G. (2024). “Pedagogical alignment of large language models”. arXiv preprint. DOI: 10.48550/arXiv.2402.05000
Tamkin, A., Liu, K., Valle, R., & Clark, J. (2025). “Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations”. Anthropic. assets.anthropic.com/m/2e23255f1e84ca97/original/Economic_Tasks_AI_Paper.pdf
Vaithilingam, P., Zhang, T., & Glassman, E. L. (2022). “Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models”. CHI EA '22: CHI Conference on Human Factors in Computing Systems Extended Abstracts, Article 332, 1–7. DOI: 10.1145/3491101.3519665
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). “Attention is all you need”. Advances in Neural Information Processing Systems, 30, 5998–6008. DOI: 10.48550/arXiv.1706.03762
Zhai, X., & Wiebe, E. (2023). “Technology-based innovative assessment”. In Classroom-Based STEM Assessment: Contemporary Issues and Perspectives, 99–125.
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P.,... & Amodei, D. (2020). “Language models are few-shot learners”. Advances in neural information processing systems, 33, 1877-1901. DOI: 10.48550/arXiv.2005.14165
Denny, P., Prather, J., Becker, B. A., Finnie-Ansley, J., Hellas, A., Leinonen, J.,... & Sarsa, S. (2024). “Computing education in the era of generative AI”. Communications of the ACM, 67(2), 56-67. DOI: 10.1145/3624720
Du Plooy, E., Casteleijn, D., & Franzsen, D. (2024). “Personalized adaptive learning in higher education: a scoping review of key characteristics and impact on academic performance and engagement”. Heliyon, 10(21), e39630. DOI: 10.1016/j.heliyon.2024.e39630
Fernández, L. R., Mena, A. L. F., Magaña, M. P. T., Magaña, M. A. R., & Fernández, M. A. R. (2024). “Inteligencia artificial en la educación: Modelo de lenguaje de gran tamaño (LLM) como recurso educativo”. Revista IPSUMTEC, 7(2), 157-164. DOI: 10.61117/ipsumtec.v7i2.321
Gao, L., Lu, J., Shao, Z., Lin, Z., Yue, S., Ieong, C.,... & Chen, S. (2024). “Fine-tuned large language model for visualization system: A study on self-regulated learning in education”. IEEE Transactions on Visualization and Computer Graphics. DOI: 10.1109/TVCG.2024.3456145
Goodfellow, I., Bengio, Y., & Courville, A. (2016). “Deep learning”. MIT Press.
Halverson, L. R., & Graham, C. R. (2019). “Learner Engagement in Blended Learning Environments: A Conceptual Framework”. Online Learning, 23, 145-178. DOI: 10.24059/olj.v23i2.1481
Johannesson, P., & Perjons, E. (2021). “An Introduction to Design Science”. In Springer eBooks. DOI: 10.1007/978-3-030-78132-3
Khan, H., Gul, R., & Zeb, M. (2023). “The Effect of Students’ Cognitive and Emotional Engagement on Students’ Academic Success and Academic Productivity”. Journal Of Social Sciences Review, 3(1), 322-334. DOI: 10.54183/jssr.v3i1.141
Lange, C. (2021). “The relationship between e-learning personalization and cognitive load”. Open Learning the Journal of Open Distance And e-Learning, 38(3), 228-242. DOI: 10.1080/02680513.2021.2019577
Levchuk, O. (2024). Diseño y evaluación de un tutor inteligente basado en Inteligencia Artificial Generativa para la adquisición de habilidades de programación. Tesis de Maestría en Ciencias. CICESE, Baja California, México. 92 pp.
Levchuk, O., Sánchez, C., Pacheco, N., López, I., & Favela, J. (2024). “Interaction Design (IxD) of an Intelligent Tutor for Programming Learning Based on LLM”. Avances en Interacción Humano-Computadora, 9(1), 1–10. DOI: 10.47756/aihc.y9i1.137
Liu, Z., He, X., Liu, L., Liu, T., & Zhai, X. (2023). “Context matters: A strategy to pre-train language model for science education”. In International Conference on Artificial Intelligence in Education, 666-674. Cham: Springer Nature Switzerland. DOI: 10.1007/978-3-031-36336-8_103
Qureshi, B. (2023). “Exploring the use of chatgpt as a tool for learning and assessment in undergraduate computer science curriculum: Opportunities and challenges”. ArXiv preprint. DOI: 10.48550/arXiv.2304.11214
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D. & Sutskever, I. (2019). “Language Models are Unsupervised Multitask Learners”. OpenAI.
Rahman, M. M., & Watanobe, Y. (2023). “ChatGPT for Education and Research: Opportunities, Threats, and Strategies”. Applied Sciences, 13(9), 5783. DOI: 10.3390/app13095783
Scherer, R., Siddiq, F., & Viveros, B. S. (2020). “A meta-analysis of teaching and learning computer programming: Effective instructional approaches and conditions”. Computers In Human Behavior, 109, 106349. DOI: 10.1016/j.chb.2020.106349
Schmucker, R., Xia, M., Azaria, A., & Mitchell, T. (2023). “Ruffle&riley: Towards the automated induction of conversational tutoring systems”. ArXiv preprint. DOI: 10.48550/arXiv.2310.01420
Singh, D., & Rajendran, R. (2024). “Cognitive engagement as a predictor of learning gain in Python programming”. Smart Learning Environments, 11(1). DOI: 10.1186/s40561-024-00330-9
Sonkar, S., Ni, K., Chaudhary, S., & Baraniuk, R. G. (2024). “Pedagogical alignment of large language models”. arXiv preprint. DOI: 10.48550/arXiv.2402.05000
Tamkin, A., Liu, K., Valle, R., & Clark, J. (2025). “Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations”. Anthropic. assets.anthropic.com/m/2e23255f1e84ca97/original/Economic_Tasks_AI_Paper.pdf
Vaithilingam, P., Zhang, T., & Glassman, E. L. (2022). “Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models”. CHI EA '22: CHI Conference on Human Factors in Computing Systems Extended Abstracts, Article 332, 1–7. DOI: 10.1145/3491101.3519665
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). “Attention is all you need”. Advances in Neural Information Processing Systems, 30, 5998–6008. DOI: 10.48550/arXiv.1706.03762
Zhai, X., & Wiebe, E. (2023). “Technology-based innovative assessment”. In Classroom-Based STEM Assessment: Contemporary Issues and Perspectives, 99–125.
Publicado
12/05/2025
Como Citar
LEVCHUK, Oleksiy.
Desarrollo y Evaluación de un Tutor Inteligente para el aprendizaje de programación basado en los Modelos de Lenguaje Extenso. In: CONGRESSO IBERO-AMERICANO EM ENGENHARIA DE SOFTWARE (CIBSE), 28. , 2025, Ciudad Real/Espanha.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 273-280.
DOI: https://doi.org/10.5753/cibse.2025.35313.
