Exploration of large language models in education: automated question and answer generation system and gamified learning environment

This project focuses on the development of a personalized and gamified learning environment powered by the automatic generation of questions and answers (Q&A-AG) using Large Language Models (LLMs). The system utilizes the Retrieval-Augmented Generation (RAG) process to analyze and extract knowledge from external documents, enabling the creation of contextually accurate and relevant Q&As. At the core of this system is an Artificially Intelligent Agent (AI-Agent) designed to evaluate students’ knowledge through gamified interactions. The agent incorporates elements such as points, streaks, and narrative-driven scenarios to enhance engagement and motivation. The system was tailored for Spanish-speaking contexts and tested to assess the accuracy, quality, and difficulty of the generated questions, as well as its impact on students’ learning experience. By combining cutting-edge AI techniques with gamification techniques, this project aims to validate its effectiveness as an innovative and scalable educational tool, offering new opportunities for personalized learning and evaluation.

• Autores: Duarte Mantilla, Ernesto José; Klopstock Triana, Nicolás
• Tipo de recurso: Trabajo de grado de pregrado
• Fecha de publicación: 2025
• Institución: Universidad de los Andes
• Repositorio: Séneca: repositorio Uniandes
• Idioma: eng
• OAI Identifier: oai:repositorio.uniandes.edu.co:1992/75407
• Acceso en línea: https://hdl.handle.net/1992/75407
• Palabra clave: Large Language Models; Gamification; Learning Environment; Retrieval-Augmented Generation; Intelligent Agent; Multi-Agent System; Question & Answer Automatic Generation; Graph-orchestrated Agents; Ingeniería
• Rights: embargoedAccess
• License: Attribution-NoDerivatives 4.0 International