2026-07-22T16:59:27Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:26739 2026-07-22T11:05:59Z ddc:004 open_access

Exploiting Generative AI to Scale up Intelligent Tutoring Systems Ferreira, Miguel Leal, José Paulo Intelligent Tutoring Systems Large language Models The research described in this paper explores the integration of Generative Artificial Intelligence (GenAI) into Intelligent Tutoring Systems (ITS) with the aim of improving programming education. Specifically, it extends Agni, a web-based programming learning platform, by automating the construction of key ITS components that are traditionally built manually. The methodology leverages Large Language Models (LLMs) to extract programming concepts from educational materials, map their relationships via concept graphs and diagnose specific student knowledge gaps. Additionally, GenAI provides real-time, contextual feedback during programming exercises, mimicking the personalized support typically offered by a human tutor. The work evaluates whether GenAI can effectively replace or augment the manual creation of domain models while preserving the pedagogical benefits of ITS. The obtained results suggest the potential of combining AI with ITS to improve scalability and reduce manual workload. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Miguel Ferreira and José Paulo Leal 2026 Is Part Of OASIcs, Volume 145, 7th International Computer Programming Education Conference (ICPEC 2026) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.ICPEC.2026.2 urn:nbn:de:0030-drops-267390 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.ICPEC.2026.2 eng https://creativecommons.org/licenses/by/4.0/legalcode