Abstract:

In the evolving landscape of higher education, the integration of Artificial Intelligence (AI) presents significant potential for strengthening active learning by enhancing student interaction and assessment practices. This study addresses the question of how AI can be leveraged to support interaction and assessment in active learning settings through a narrative literature review. The review synthesizes findings from fourteen recent, peer-reviewed studies published between 2022 and 2025, identified through systematic searches of Scopus, Web of Science, and Google Scholar using keywords related to AI, active learning, student interaction, formative assessment, and feedback. Studies were selected based on relevance to higher education contexts and a clear focus on AI-supported interaction and/or assessment, and were analyzed using a thematic and conceptual synthesis approach.

The reviewed literature examines a range of active learning tools and practices augmented by AI, including conversational agents and intelligent tutoring systems, adaptive and automated assessment platforms, AI-supported peer assessment, and learning analytics dashboards. Findings indicate consistent patterns of enhanced engagement, improved immediacy and quality of formative feedback, and increased alignment between assessment and learning processes when AI is integrated into student-centered pedagogical designs. Building on these themes, the paper proposes a conceptual AI-enhanced active learning framework that integrates interaction, assessment, feedback, and personalization within an iterative learning cycle, while explicitly positioning AI as an enabling layer rather than a replacement for human instruction.

Claims regarding the framework’s potential efficacy are grounded in conceptual modeling and convergence of evidence across the reviewed studies, rather than direct empirical validation. While the framework has not yet been implemented or tested, the synthesis suggests that its components are theoretically aligned with constructivist and active learning principles and reflect empirically supported affordances of AI reported in prior research. The article concludes by outlining directions for future empirical studies to validate the framework’s effectiveness, scalability, and long-term impact on learning outcomes across disciplinary contexts.

Keywords:

Artificial Intelligence in Education, Active Learning, Student Interaction, Personalized Assessment, Intelligent Tutoring Systems.