Multi-Intelligent Agents and Generative AI in Learner Assessment: A Scoping Review of Research Trends, Challenges, and Hybrid Opportunities
Haythem Chniti, Asma Hadyaoui, Lilia Cheniti‐Belcadhi · Procedia Computer Science · 2025
This paper presents a comprehensive review of the integration of Multi-Intelligent Agents (MIA) and Generative AI (GenAI) in learner assessment. Through a systematic bibliometric analysis of literature from 2019 to 2024, we identify key research trends, methodologies, and applications in educational contexts. Our findings reveal that MIA excels in orchestrating adaptive and collaborative assessments (34.6% of research), while GenAI demonstrates significant potential in higher education (50% of research) for content generation and personalized feedback. The combined approach remains underexplored (14.6% of studies) but shows promise for developing more effective assessment frameworks. This study contributes to the field by mapping the evolution of MIA and GenAI in assessment, identifying current gaps in empirical validation, and proposing a hybrid model that enhances both automation and personalization. It offers a critical perspective on practical challenges and ethical concerns, setting a structured research agenda for future explorations.