EduVerse: A User-Defined Multi-Agent Simulation Space for Education Scenario

2025-10-07

AI Summary

This study addresses the challenge of jointly modeling open-ended cognition, dynamic social interaction, affective factors, and multi-stage development in authentic classroom settings. We propose the first user-customizable multi-agent educational simulation framework. Methodologically, we design a scalable virtual classroom based on a hierarchical Cognition-Interaction-Evolution (CIE) architecture, integrating large language model–driven agent behavior modeling, social network analysis, affective computing, and cross-session state tracking; we further introduce a novel human-in-the-loop interface to embed real users. Contributions include: (1) establishing a closed-loop CIE modeling paradigm, and (2) balancing pedagogical authenticity with experimental reproducibility. Evaluation in middle-school Chinese language classrooms demonstrates high fidelity to Initiation-Response-Follow-up (IRF) discourse patterns, group interaction network density ranging from 0.27 to 0.40, and an average 11.7% increase in cross-session positive behavioral transfer rate.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Reproducing cognitive development, group interaction, and long-term evolution in virtual classrooms remains a core challenge for educational AI, as real classrooms integrate open-ended cognition, dynamic social interaction, affective factors, and multi-session development rarely captured together. Existing approaches mostly focus on short-term or single-agent settings, limiting systematic study of classroom complexity and cross-task reuse. We present EduVerse, the first user-defined multi-agent simulation space that supports environment, agent, and session customization. A distinctive human-in-the-loop interface further allows real users to join the space. Built on a layered CIE (Cognition-Interaction-Evolution) architecture, EduVerse ensures individual consistency, authentic interaction, and longitudinal adaptation in cognition, emotion, and behavior-reproducing realistic classroom dynamics with seamless human-agent integration. We validate EduVerse in middle-school Chinese classes across three text genres, environments, and multiple sessions. Results show: (1) Instructional alignment: simulated IRF rates (0.28-0.64) closely match real classrooms (0.37-0.49), indicating pedagogical realism; (2) Group interaction and role differentiation: network density (0.27-0.40) with about one-third of peer links realized, while human-agent tasks indicate a balance between individual variability and instructional stability; (3) Cross-session evolution: the positive transition rate R+ increase by 11.7% on average, capturing longitudinal shifts in behavior, emotion, and cognition and revealing structured learning trajectories. Overall, EduVerse balances realism, reproducibility, and interpretability, providing a scalable platform for educational AI. The system will be open-sourced to foster cross-disciplinary research.

Problem

• Reproducing cognitive development and social interaction in virtual classrooms
• Addressing limitations of short-term or single-agent educational AI settings
• Creating realistic classroom dynamics with seamless human-agent integration

Innovation

• User-defined multi-agent simulation space for education
• Layered CIE architecture for cognition and interaction
• Human-in-the-loop interface enabling real user participation