EduMirror: Modeling Educational Social Dynamics with Value-driven Multi-agent Simulation

Jingzhe Lin, Hengbin Yu, Yongdan Zeng, Fangwei Zhong
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:75105-75160, 2026.

Abstract

Understanding how educational social dynamics evolve is critical for informing effective educational policies and counterfactual interventions. However, traditional methods face a fundamental dilemma: observational studies often lack causal power, while controlled experiments are frequently constrained by ethical concerns. Although LLM-based multi-agent simulations offer a scalable in silico alternative, existing approaches remain limited by weak psychological grounding and insufficient measurement of latent psychological states. To address this, we introduce EduMirror, a multi-agent simulator for the scientific study of educational social dynamics. We provide configurable education-oriented agent forms, including value-driven agents grounded in psychological needs and social value orientation, together with a dual-track measurement protocol for quantifying observable behaviors and latent psychological states. We validate the realism and usability of EduMirror through case studies on school bullying and group cooperation, as well as broader evaluations across diverse educational scenarios. The results show that EduMirror generates educational social dynamics that are realistic, theory-consistent, and measurable by empirical criteria. These properties enable structured in silico educational research, providing a computational tool for hypothesis testing and counterfactual intervention analysis in educational science. Project page: https://edumirror.net.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-lin26aq, title = {{E}du{M}irror: Modeling Educational Social Dynamics with Value-driven Multi-agent Simulation}, author = {Lin, Jingzhe and Yu, Hengbin and Zeng, Yongdan and Zhong, Fangwei}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {75105--75160}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/lin26aq/lin26aq.pdf}, url = {https://proceedings.mlr.press/v306/lin26aq.html}, abstract = {Understanding how educational social dynamics evolve is critical for informing effective educational policies and counterfactual interventions. However, traditional methods face a fundamental dilemma: observational studies often lack causal power, while controlled experiments are frequently constrained by ethical concerns. Although LLM-based multi-agent simulations offer a scalable in silico alternative, existing approaches remain limited by weak psychological grounding and insufficient measurement of latent psychological states. To address this, we introduce EduMirror, a multi-agent simulator for the scientific study of educational social dynamics. We provide configurable education-oriented agent forms, including value-driven agents grounded in psychological needs and social value orientation, together with a dual-track measurement protocol for quantifying observable behaviors and latent psychological states. We validate the realism and usability of EduMirror through case studies on school bullying and group cooperation, as well as broader evaluations across diverse educational scenarios. The results show that EduMirror generates educational social dynamics that are realistic, theory-consistent, and measurable by empirical criteria. These properties enable structured in silico educational research, providing a computational tool for hypothesis testing and counterfactual intervention analysis in educational science. Project page: https://edumirror.net.} }
Endnote
%0 Conference Paper %T EduMirror: Modeling Educational Social Dynamics with Value-driven Multi-agent Simulation %A Jingzhe Lin %A Hengbin Yu %A Yongdan Zeng %A Fangwei Zhong %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-lin26aq %I PMLR %P 75105--75160 %U https://proceedings.mlr.press/v306/lin26aq.html %V 306 %X Understanding how educational social dynamics evolve is critical for informing effective educational policies and counterfactual interventions. However, traditional methods face a fundamental dilemma: observational studies often lack causal power, while controlled experiments are frequently constrained by ethical concerns. Although LLM-based multi-agent simulations offer a scalable in silico alternative, existing approaches remain limited by weak psychological grounding and insufficient measurement of latent psychological states. To address this, we introduce EduMirror, a multi-agent simulator for the scientific study of educational social dynamics. We provide configurable education-oriented agent forms, including value-driven agents grounded in psychological needs and social value orientation, together with a dual-track measurement protocol for quantifying observable behaviors and latent psychological states. We validate the realism and usability of EduMirror through case studies on school bullying and group cooperation, as well as broader evaluations across diverse educational scenarios. The results show that EduMirror generates educational social dynamics that are realistic, theory-consistent, and measurable by empirical criteria. These properties enable structured in silico educational research, providing a computational tool for hypothesis testing and counterfactual intervention analysis in educational science. Project page: https://edumirror.net.
APA
Lin, J., Yu, H., Zeng, Y. & Zhong, F.. (2026). EduMirror: Modeling Educational Social Dynamics with Value-driven Multi-agent Simulation. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:75105-75160 Available from https://proceedings.mlr.press/v306/lin26aq.html.

Related Material