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

• URL: http://arxiv.org/abs/2606.07948v1
• Date: Sat, 06 Jun 2026 02:38:30 GMT
• Title: EduMirror: Modeling Educational Social Dynamics with Value-driven Multi-agent Simulation
• Abstract summary: EduMirror is a multi-agent simulator for the scientific study of educational social dynamics.<n>We provide education-oriented agent forms, including value-driven agents grounded in psychological needs and social value orientation.<n>We validate the realism and usability of EduMirror through case studies on school bullying and group cooperation.
• Score: 10.520958874634399
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation [52.11732144306638]
  "Memory-Augmented Social Simulation" (MASS) is an innovative paradigm that leverages highly realistic and research-oriented social simulations.<n>Specifically, MASS integrates three core components: dynamic goal-path planning with multi-level social norm restraint to guide the simulation, a multi-disciplinary behavior dataset for agent memory cold-start, and a structured forgetting mechanism inspired by the Ebbinghaus curve.
  arXiv  Detail & Related papers  (2026-06-08T08:32:21Z)
• AgentSchool: An LLM-Powered Multi-Agent Simulation for Education [64.62476927093753]
  AgentSchool is a multi-agent simulator that models learning as state transition rather than prompted behavior.<n>It generates plausible traces of peripheral participation, clique formation, aggressor-induced cohesion, and opinion-leader emergence.<n>AgentSchool frames education as a socially meaningful testbed for long-horizon memory, multi-agent coordination, and future institutional reasoning.
  arXiv  Detail & Related papers  (2026-05-28T16:05:58Z)
• A Survey of Large Language Models for Perception and Measurement of Human Psychology [55.608047817598965]
  A central issue is whether Large Language Models possess the capability to accurately perceive and measure complex, latent human psychological constructs.<n>This paper provides a systematic review focused on the use of LLMs as instruments for human psychological measurement.
  arXiv  Detail & Related papers  (2026-05-20T14:54:09Z)
• Mechanism Plausibility in Generative Agent-Based Modeling [3.8124330987881137]
  Large language models (LLMs) can generate high-level diverse phenomena without explicitly programmed rules.<n>Recent studies investigate their ability to generate different phenomena of interest, for example, human behavior on social media platforms or alien behavior in game-theoretic scenarios.<n>We use recent work on LLM-ABMs with contemporary philosophy of science literature to operationalize a definition of 'plausibility' in a four-level scale.
  arXiv  Detail & Related papers  (2026-05-12T23:46:39Z)
• Leveraging LLM-based agents for social science research: insights from citation network simulations [132.4334196445918]
  We introduce the CiteAgent framework, designed to generate citation networks based on human-behavior simulation.<n>CiteAgent captures predominant phenomena in real-world citation networks, including power-law distribution, citational distortion, and shrinking diameter.<n>We establish two LLM-based research paradigms in social science, allowing us to validate and challenge existing theories.
  arXiv  Detail & Related papers  (2025-11-05T08:47:04Z)
• A Multi-Agent Psychological Simulation System for Human Behavior Modeling [4.254136484646083]
  Training and education in human-centered fields require authentic practice, yet realistic simulations of human behavior have remained limited.<n>We present a multi-agent psychological simulation system that models internal cognitive-affective processes to generate believable human behaviors.
  arXiv  Detail & Related papers  (2025-11-04T14:28:03Z)
• Social Simulations with Large Language Model Risk Utopian Illusion [61.358959720048354]
  We introduce a systematic framework for analyzing large language models' behavior in social simulation.<n>Our approach simulates multi-agent interactions through chatroom-style conversations and analyzes them across five linguistic dimensions.<n>Our findings reveal that LLMs do not faithfully reproduce genuine human behavior but instead reflect overly idealized versions of it.
  arXiv  Detail & Related papers  (2025-10-24T06:08:41Z)
• Large Language Models as Psychological Simulators: A Methodological Guide [0.0]
  This article provides a framework for using large language models as psychological simulators across two primary applications.<n>For simulation, we present methods for developing psychologically grounded personas that move beyond demographic categories.<n>We address overarching challenges including prompt sensitivity, temporal limitations from training data cutoffs, and ethical considerations that extend beyond traditional human subjects review.
  arXiv  Detail & Related papers  (2025-06-20T02:45:23Z)
• From Prompts to Constructs: A Dual-Validity Framework for LLM Research in Psychology [0.0]
  We argue that building a robust science of AI psychology requires integrating the principles of reliable measurement and the standards for sound causal inference.<n>We present a dual-validity framework to guide this integration, which clarifies how the evidence needed to support a claim scales with its scientific ambition.
  arXiv  Detail & Related papers  (2025-06-20T02:38:42Z)
• AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society [32.849311155921264]
  We propose AgentSociety, a large-scale social simulator that integrates a realistic societal environment.<n>Based on the proposed simulator, we generate social lives for over 10k agents, simulating their 5 million interactions.<n>We focus on four key social issues: polarization, the spread of inflammatory messages, the effects of universal basic income policies, and the impact of external shocks such as hurricanes.
  arXiv  Detail & Related papers  (2025-02-12T15:27:07Z)
• Synthetic Social Media Influence Experimentation via an Agentic Reinforcement Learning Large Language Model Bot [7.242974711907219]
  This study provides a novel simulated environment that combines agentic intelligence with Large Language Models (LLMs) to test topic-specific influence mechanisms.<n>Our framework contains agents that generate posts, form opinions on specific topics, and socially follow/unfollow each other based on the outcome of discussions.
  arXiv  Detail & Related papers  (2024-11-29T11:37:12Z)
• PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
  We propose PersLLM, a framework for better data construction and model tuning.<n>For insufficient data usage, we incorporate strategies such as Chain-of-Thought prompting and anti-induction.<n>For rigid behavior patterns, we design the tuning process and introduce automated DPO to enhance the specificity and dynamism of the models' personalities.
  arXiv  Detail & Related papers  (2024-07-17T08:13:22Z)
• Empirical Estimates on Hand Manipulation are Recoverable: A Step Towards Individualized and Explainable Robotic Support in Everyday Activities [80.37857025201036]
  Key challenge for robotic systems is to figure out the behavior of another agent. Processing correct inferences is especially challenging when (confounding) factors are not controlled experimentally. We propose equipping robots with the necessary tools to conduct observational studies on people.
  arXiv  Detail & Related papers  (2022-01-27T22:15:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.