Mapping Student-AI Interaction Dynamics in Multi-Agent Learning Environments: Supporting Personalised Learning and Reducing Performance Gaps

2025-06-03

AI Summary

This study investigates interaction patterns between students and teacher-/peer-like AI agents in a multi-agent AI learning environment (MAIC platform) and their effects on cognitive (learning gains) and non-cognitive outcomes (motivation, technology acceptance). Drawing on 19,365 dialogues and pre-post data from 305 undergraduate students, we identify—through mixed-methods analysis combining lag sequential analysis, cognitive assessments, and validated scales—two dynamic interaction patterns: “knowledge co-construction” and “collaborative regulation.” Results show that students with low prior knowledge achieve significantly greater learning gains (*p* < .01) and enhanced intrinsic motivation (*d* = 0.42) through knowledge co-construction, providing mechanistic evidence for reducing achievement gaps. Furthermore, the multi-agent system demonstrates adaptive personalization: low-proficiency learners benefit disproportionately, while overall technology acceptance improves across all groups—supporting scalable, equitable, and personalized educational interventions.

Technology Category

• Multiagent Systems: Multiagent Learning
• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Multi-agent AI systems, which simulate diverse instructional roles such as teachers and peers, offer new possibilities for personalized and interactive learning. Yet, student-AI interaction patterns and their pedagogical implications remain unclear. This study explores how university students engaged with multiple AI agents, and how these interactions influenced cognitive outcomes (learning gains) and non-cognitive factors (motivation, technology acceptance). Based on MAIC, an online learning platform with multi-agent, the research involved 305 university students and 19,365 lines of dialogue data. Pre- and post-test scores, self-reported motivation and technology acceptance were also collected. The study identified two engagement patterns: co-construction of knowledge and co-regulation. Lag sequential analysis revealed that students with lower prior knowledge relied more on co-construction of knowledge sequences, showing higher learning gains and post-course motivation. In contrast, students with higher prior knowledge engaged more in co-regulation behaviors but exhibited limited learning improvement. Technology acceptance increased across all groups. These findings suggest that multi-agent AI systems can adapt to students' varying needs, support differentiated engagement, and reduce performance gaps. Implications for personalized system design and future research directions are discussed.

Problem

• Understanding student-AI interaction patterns in multi-agent learning environments
• Assessing impact of AI interactions on cognitive and non-cognitive outcomes
• Exploring AI's role in personalized learning and reducing performance gaps

Innovation

• Multi-agent AI system simulates instructional roles
• MAIC platform analyzes student-AI dialogue patterns
• Adaptive engagement reduces learning performance gaps