Integration of AI and Metaheuristics in Educational Software: A Hybrid Approach to Exercise Generation

Abstract

This study explores the integration of generative artificial intelligence (AI) with Exercise Generation Algorithm+ (EGAL+), a multi-objective harmony search (HS) metaheuristic-based algorithm capable of composing high-quality exercises. These exercises are characterized by their diversity, consistent difficulty, and comprehensive coverage of the source material, tailored to user preferences. One of the main challenges of using metaheuristics to compile exercises efficiently is the initial creation of a large question bank, which often demands significant time and effort from instructors. To overcome this challenge, the integration of a readily available existing generative AI module is proposed. This module is accessed through its application programming interface, autonomously populating the question bank. This sets the stage for EGAL+ to fine-tune the selection and assembly of specific exams. The resulting program enables educators to create an extensive question bank from any educational material, independent of the subject, and subsequently compose exercises with minimal effort. This approach leverages the synergistic benefits of both generative AI and metaheuristicbased optimization, offering a robust and efficient solution for exercise generation.