Inteligencia artificial en educación superior: arquitecturas agénticas, feedback y enfoques pedagógicos emergentes. Una revisión de alcance 2024-2026
DOI:
https://doi.org/10.47606/ACVEN/PH0588Palabras clave:
inteligencia artificial agéntica, educación superior, feedback; RAG, sistemas multiagente, revisión de alcanceResumen
Recientes trabajos sobre IA en la educación superior empiezan a evidenciar un cambio de paradigma, de herramientas generativas aisladas a configuraciones más integradas. La presente revisión de alcance analizó la evidencia de los años 2024-2026, centrándose en las arquitecturas agénticas, feedback, personalización, funciones pedagógicas y supervisión humana. En la búsqueda que se realizó el 15 de agosto de 2026 en las bases de datos Scopus, Web of Science, ERIC, SciELO y Redalyc se encontraron 406 registros. Fueron incluidos 44 estudios para extracción y síntesis después del proceso de selección reportado mediante PRISMA-ScR. A partir de su lectura se reconocieron seis ejes, que posteriormente se organizaron en tres dimensiones: apoyo al aprendizaje, competencias e infraestructura, y condiciones de implementación. Entre los hallazgos, las arquitecturas agénticas mostraron una mayor explicitud técnica, mientras que la personalización y el feedback concentraron buena parte de las aplicaciones pedagógicas. Sin embargo, esa mayor complejidad técnica no estuvo acompañada de evidencia educativa con el mismo grado de desarrollo. Persisten vacíos en aprendizaje profundo, transferencia, equidad y evaluación longitudinal, lo que limita todavía la valoración de efectos educativos sostenidos.
Descargas
Citas
Aguirre Tucto, J. S., Crespo Barrionuevo, K. B., Bernuy Pimentel, J. J., & Rios García, G. (2026). Componentes teóricos y metodológicos de la IA generativa en competencias investigativas universitarias: Revisión sistemática. Revista Aula Virtual, 7(15), 1–23. https://doi.org/10.5281/zenodo.21309447
Anghel, C., Anghel, A. A., Craciun, M. V., Cocu, A., Vulpe, D.-E., Andrei, C. A., Maier, C., Scheau, C., Dragosloveanu, S., & Cergan, R. (2026). GradeAgentOps: A verification-first framework for evidence-anchored LLM exam grading. AI, 7(6), Article 198. https://doi.org/10.3390/ai7060198
Arguson, A. C., Sabonsolin, J. A., Malasaga, E. V., & Ramos, R. F. (2026). A hybrid framework for LMS web analytics: Combining clickstream analysis and sentiment mining for retention prediction. In Proceedings of the 9th International Conference on Computers in Management and Business (ICCMB 2026, pp. 173–179). Association for Computing Machinery. https://doi.org/10.1145/3802463.3802490
Arksey, H., & O’Malley, L. (2005). Scoping studies: Towards a methodological framework. International Journal of Social Research Methodology, 8(1), 19–32. https://doi.org/10.1080/1364557032000119616
Badger, M., López, N., & Nissen, C. F. R. (2026). The impact of GenAI chatbots on student learning in higher education: A literature review. International Journal of Technology in Education, 9(1), 43–69. https://doi.org/10.46328/ijte.5111
Bai, H., Lui, W. C., & Khiatani, P. V. (2025). Promoting student engagement with GPTutor: An intelligent tutoring system powered by generative AI. International Journal of Educational Technology in Higher Education, 22, Article 77. https://doi.org/10.1186/s41239-025-00571-9
Belawati, T., & Prasetyo, D. (2025). Generative AI-based tutoring for enhancing learning engagement and achievement. Open Praxis, 17(2), 211–226. https://doi.org/10.55982/openpraxis.17.2.902
Bozkurt, A., Crompton, H., Farrow, R., Kukulska-Hulme, A., Dron, J., West, R., Palalas, A., Bower, M., Xiao, J., Tlili, A., Henriksen, D., Pazurek, A., Huijser, H., Chiu, T. K. F., Jandri?, P., Jordan, K., Curry, J., Kimmons, R., Cukurova, M., Reeves, T., Hwang, G.-J., Shea, P., Lodge, J., Weller, M., Ng, D., & Asino, T. I. (2026). Redefining educational technology: A critical collaborative inquiry. Open Praxis, 18(2), 192–211. https://doi.org/10.55982/openpraxis.18.2.1117
Cai, Y. (2026). A multi-agent collaborative system for student writing assistance: An empirical study on mitigating AI bias and hallucination. In Proceedings of the 2026 International Conference on Big Data and Informatization Education (ICBDIE ’26) (pp. 314–321). Association for Computing Machinery. https://doi.org/10.1145/3806980.3807031
Celik, I., Gedrimiene, E., Siklander, S., & Muukkonen, H. (2024). The affordances of artificial intelligence-based tools for supporting 21st-century skills: A systematic review of empirical research in higher education. Australasian Journal of Educational Technology, 40(3), 19–38. https://doi.org/10.14742/ajet.9609
Chafloque-Capuñay, J. E., Uría-Sánchez, M. B., Gonzales-Velásquez, E. A., Borges-Huanca, A., Marocho-Rojas, A., & Ussa-Lopez, Y. E. (2026). Inteligencia artificial generativa y escritura académica en la educación superior: Revisión integrativa de sus implicaciones pedagógicas, éticas y evaluativas. Prohominum, 8(2), 247–262. https://doi.org/10.47606/ACVEN/PH0487
Deng, X., Miletic, V., Trinh, E., Gao, J., Xu, C., & Liu, D. (2026). DentEval: Fine-tuning-free expert-aligned assessment in dental education via LLM agents. In J. C. Gee, J. Hong, C. H. Sudre, P. Golland, D. C. Alexander, J. E. Iglesias, A. Venkataraman, & J. H. Kim (Eds.), Medical Image Computing and Computer Assisted Intervention, MICCAI 2025 - 28th International Conference, 2025, Proceedings (pp. 144–153). Springer. https://doi.org/10.1007/978-3-032-04971-1_14
Düsterbeck, L. M., Größler, M., Credidio, G., Bellmann, L., & Riemann, L. T. (2026). Node-Sampling: Adaptive multi-agent optimization in medical education. Frontiers in Computer Science, 8, Article 1758333. https://doi.org/10.3389/fcomp.2026.1758333
Espino, L. C., Antonio, R. P., Constantino, W. R., Espino, C. L., & Wider, W. (2026). Artificial intelligence-driven teaching methods for enhancing higher quality education: A bibliometric analysis. International Journal of Technology in Education, 9(1), 153–167. https://doi.org/10.46328/ijte.5114
Fan, Y., Tang, L., Le, H., Shen, K., Tan, S., Zhao, Y., Shen, Y., Li, X., & Gaševi?, D. (2025). Beware of metacognitive laziness: Effects of generative artificial intelligence on learning motivation, processes, and performance. British Journal of Educational Technology, 56(2), 489–530. https://doi.org/10.1111/bjet.13544
Hattab, S., & Ziadi, F. (2026). Towards secure and transparent practical assessments in computer science: A multi-agent and blockchain-based architecture. In Proceedings of the 18th International Conference on Agents and Artificial Intelligence (ICAART 2026) (Vol. 1, pp. 504–511). SCITEPRESS. https://doi.org/10.5220/0014412600004052
Hu, Y.-H., Yu, H.-Y., & Hsieh, C.-L. (2025). Can pedagogical agent-based scaffolding boost information problem-solving in one-on-one collaborative learning with a virtual learning companion? Education and Information Technologies. Advance online publication. https://doi.org/10.1007/s10639-025-13784-2
Hu, Z., Paprotskyi, M.-M., Vysotska, V., Chyrun, L., Ushenko, Y., & Uhryn, D. (2025). Local agentic RAG-based information system development for intelligent analysis of GitHub code repositories in computer science education. International Journal of Modern Education and Computer Science, 17(5), 109–145. https://doi.org/10.5815/ijmecs.2025.05.07
Huang, C.-Q., Lu, L.-N., Huang, Q.-H., Zhang, Y.-R., He, T., Tu, Y.-F., & Hwang, G.-J. (2026). Effects of artificial intelligence feedback on students’ self-regulated learning in higher education: A three-level meta-analysis. Educational Psychology Review. Advance online publication. https://doi.org/10.1007/s10648-026-10166-z
Klepikov, O. E., Pozdnyakova, E. M., & Sizov, Y. O. (2026). From measurement to understanding: An architecture of emulated expertise for LLM-diagnostics in education. Psychology. Journal of the Higher School of Economics, 23(2), 263–274. https://doi.org/10.17323/1813-8918-2026-2-263-274
Kundu, S., Chatterjee, A., Dhokne, N., Goyal, R. K., & Mishra, S. (2026). AgiQ-A: An agentic question-answer pairing system to aid handwritten answer sheet evaluation. In Proceedings of the 18th International Conference on Computer Supported Education (CSEDU 2026) (Vol. 1, pp. 94–105). SCITEPRESS. https://doi.org/10.5220/0014820600004021
Larrea Eyzaguirre, J. C., & Bustillos Torrez, W. (2025). La inteligencia artificial generativa en la educación odontológica: Una revisión narrativa de aplicaciones y desafíos. Revista de la Asociación Odontológica Argentina, 113(3), Artículo e1131252. https://doi.org/10.52979/raoa.1131252.1306
Le, H., Shen, Y., Li, Z., Xia, M., Tang, L., Li, X., Jia, J., Wang, Q., Gaševi?, D., & Fan, Y. (2025). Breaking human dominance: Investigating learners' preferences for learning feedback from generative AI and human tutors. British Journal of Educational Technology, 56(5), 1758–1783. https://doi.org/10.1111/bjet.13614
Letteri, I., & Vittorini, P. (2025). Enhancing student feedback in data science education: Harnessing the power of AI-generated approaches. International Journal of Artificial Intelligence in Education, 35, 3071–3094. https://doi.org/10.1007/s40593-025-00492-8
Levac, D., Colquhoun, H., & O’Brien, K. K. (2010). Scoping studies: Advancing the methodology. Implementation Science, 5, 69. https://doi.org/10.1186/1748-5908-5-69
López-Goyez, J. P., González-Briones, A., & Demazeau, Y. (2026a). An adaptive multi-agent architecture with reinforcement learning and generative AI for intelligent tutoring systems: A Moodle-based case study. Applied Sciences, 16(3), Article 1323. https://doi.org/10.3390/app16031323
López-Goyez, J. P., González-Briones, A., Demazeau, Y., & Guaytarilla G., J. M. (2026b). An exploratory study of a generative AI-based intelligent tutoring system using a multi-agent architecture in higher education. Applied Sciences, 16(11), Article 5453. https://doi.org/10.3390/app16115453
Modran, H. A. (2025). Leveraging RAG with ACP & MCP for adaptive intelligent tutoring. Applied Sciences, 15(21), Article 11443. https://doi.org/10.3390/app152111443
Nendauni, L. (2025). Whose feedback matters? Exploring human and AI-supported writing feedback practices in a South African writing centre. Journal of Learning Development in Higher Education, 38. https://doi.org/10.47408/jldhe.vi38
Page, M. J., McKenzie, J. E., Bossuyt, P. M., et al. (2021). The PRISMA 2020 statement: An updated guideline for reporting systematic reviews. BMJ, 372, n71. https://doi.org/10.1136/bmj.n71
Pan, J., Hu, Y., & Chen, H. (2026). A technology-enhanced learning framework for college English writing: Orchestrating generative AI agents in process-based instruction. In Proceedings of the 3rd International Conference on Informatics Education and Computer Technology Applications (IECA 2026, pp. 930–937). Association for Computing Machinery. https://doi.org/10.1145/3802133.3802283
Peters, M. D. J., Godfrey, C., McInerney, P., Munn, Z., Tricco, A. C., & Khalil, H. (2024). Scoping reviews. In E. Aromataris, C. Lockwood, K. Porritt, B. Pilla, & Z. Jordan (Eds.), JBI Manual for Evidence Synthesis. JBI. https://doi.org/10.46658/JBIMES-24-09
Qiu, C., Cui, K., & Wang, Z. (2026). Personalized driven instruction through explainable agentic AI in multicultural higher education environments. Big Data. Advance online publication. https://doi.org/10.1177/2167647X261463927
Rahman, A., Khandakar, A., Ayari, M. A., Naji, K., Al-Ali, A. K., Sellami, A. L., & Alhazbi, S. M. A. (2026). Artificial intelligence innovations, challenges and emerging trends in engineering education. Discover Education, 5, Artículo 179. https://doi.org/10.1007/s44217-026-01137-1
Rethlefsen, M. L., Kirtley, S., Waffenschmidt, S., Ayala, A. P., Moher, D., Page, M. J., & Koffel, J. B. (2021). PRISMA-S: An extension to the PRISMA statement for reporting literature searches in systematic reviews. Systematic Reviews, 10, Article 39. https://doi.org/10.1186/s13643-020-01542-z
Simarco-Scarci, A., Fonseca, M. H., Moser-Teixeira, T., & Fleig-Dal Forno, L. (2026). Gestión del conocimiento e inteligencia artificial en la educación superior. Alteridad, 21(1), 108–122. https://doi.org/10.17163/alt.v21n1.2026.08
Tamascelli, M., Bunch, O., Fowler, B., Taeb, M., & Cohen, A. (2025). Academic advising chatbot powered with AI agent. Proceedings of the 2025 ACM Southeast Conference, 195–202. https://doi.org/10.1145/3696673.3723065
Tang, K., Chen, K., Gopi, S., Xie, L., Quinlan, M., & Cho, Y. (2026). GamifiedLM: Co-designing an LLM-driven gamified learning app with university students to mitigate learning difficulties. In Proceedings of the 2026 Designing Interactive Systems Conference (DIS ’26, pp. 2450–2473). ACM. https://doi.org/10.1145/3800645.3812916
Tricco, A. C., Lillie, E., Zarin, W., O’Brien, K. K., Colquhoun, H., Levac, D., Moher, D., Peters, M. D. J., Horsley, T., Weeks, L., Hempel, S., Akl, E. A., Chang, C., McGowan, J., Stewart, L., Hartling, L., Aldcroft, A., Wilson, M. G., Garritty, C., … Straus, S. E. (2018). PRISMA extension for scoping reviews (PRISMA-ScR): Checklist and explanation. Annals of Internal Medicine, 169(7), 467–473. https://doi.org/10.7326/M18-0850
Wang, G., & Sun, F. (2026). Effect of artificial intelligence-based tutoring, cognitive engagement, and teacher feedback on university students’ academic performance. European Journal of Education, 61(2), Article e70619. https://doi.org/10.1111/ejed.70619
Xie, Y., Fan, Z., Pei, J., Sun, Y., & Chang, K.-W. (2026). SlideBot: A multi-agent framework for generating informative, reliable, multi-modal presentations. Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM ’26, pp. 1–10). Association for Computing Machinery. https://doi.org/10.1145/3789876.3789901
Yi, Y., & Wu, X. (2025). Cognitive load early warning based on behavioral data: A single-agent approach for dynamically adjusting task difficulty. In Proceedings of the 2nd International Conference on Big Data Analytics and Artificial Intelligence Application (BDAIA 2025, pp. 140–144). Association for Computing Machinery. https://doi.org/10.1145/3788108.3788518
Zhong, X., & Zhan, Z. (2025). An intelligent tutoring system for programming education based on informative tutoring feedback: System development, algorithm design, and empirical study. Interactive Technology and Smart Education, 22(1), 3–24. https://doi.org/10.1108/ITSE-09-2023-0182
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2026 José Eugenio Chafloque Capuñay , Elsa Dolores Hernández García , Mariluz Herrera Cervantes , Germán Vicente Garay-Flores , Guadalupe Badillo Márquez , Gladys Huarachi Chuquimia
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
