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

Yiping Ma, Shiyu Hu, Zhu Buyuan, Yipei Wang, Yaxuan Kang, Shiqing Liu, Kang Hao Cheong

Keywords: AI4Education; Large Language Models; Educational AI

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.
\textcolor{blue}{We present \textbf{EduVerse}, \textcolor{blue}{one of the first} \emph{user-defined} multi-agent classroom simulator supporting customizable environment, customizable agents, and multi-session evolution.} A distinctive human-in-the-loop interface further allows real users to join the space. Built on a layered \textbf{CIE} (\textbf{C}ognition–\textbf{I}nteraction–\textbf{E}volution) 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: \textbf{(i) Instructional alignment}: simulated \textcolor{blue}{Initiate-Response-Feedback (IRF)} rates ($0.34$--$0.55$) closely match real classrooms ($0.37$--$0.49$), indicating pedagogical realism; \textbf{(ii) 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; \textbf{(iii) 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;
\textcolor{blue}{\textbf{(iv) Cross-disciplinary generalization}: without any additional tuning, IRF rates and peer-interaction topologies naturally adapt to the discourse characteristics of history instruction while preserving the core instructional structure, demonstrating robust cross-disciplinary transfer.}
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.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 11118