2026-08-14T12:00:16Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:24043 2025-12-12T14:58:39Z ddc:004 open_access

Interactive Evaluation of Complex Programming Assignments Using LLM Assistant Kormaník, Tomáš Lukáčová, Viktória Porubän, Jaroslav Artificial Intelligence Generative Models Programming Assessment Software Engineering Education Generative language models present significant advancements in artificial intelligence with increasing applications in software engineering education. This paper explores the potential of customized generative dialogue models for automated assessment of programming assignments. The research introduces KP Assistant, a tailored implementation based on GPT-4o developed for a Component Programming university course. The research evaluated the effectiveness of this approach in generating relevant questions about source code, assessing student understanding, and providing objective feedback through a series of experiments with various game implementations and student testing. The findings demonstrate the feasibility of integrating such models into educational workflows while also acknowledging their present limitations. The study provides a framework for implementing similar systems in programming education, showing how generative AI can augment traditional assessment methods while maintaining pedagogical integrity. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Tomáš Kormaník and Viktória Lukáčová and Jaroslav Porubän 2025 Is Part Of OASIcs, Volume 133, 6th International Computer Programming Education Conference (ICPEC 2025) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.ICPEC.2025.13 urn:nbn:de:0030-drops-240438 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.ICPEC.2025.13 eng https://creativecommons.org/licenses/by/4.0/legalcode