Personality-Driven Student Agent-Based Modeling in Mathematics Education: How Well Do Student Agents Align with Human Learners?

2026-03-22

AI Summary

This work proposes a large language model–based student agent modeling paradigm to effectively evaluate the impact of teaching methods on student learning while circumventing ethical constraints. The framework systematically integrates the Big Five personality theory for the first time, comprehensively simulating the full spectrum of student behaviors—including teacher–student interaction, self-directed learning, and examination performance. To quantitatively assess behavioral alignment between agents and human learners, the study introduces 14 behavioral consistency criteria. Experimental results demonstrate that 71.4% of the simulated agent behaviors align with findings from empirical human studies across these criteria, thereby validating the efficacy and credibility of the proposed approach in educational simulation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Humans and AI: Learning Human Values and Preferences

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: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

It is crucial to explore the impact of different teaching methods on student learning in educational research. However, real-person experiments face significant ethical constraints, and we cannot conduct repeated teaching experiments on the same student. LLM-based generative agents offer a promising avenue for simulating student behavior. Before large-scale experiments, a fundamental question must be addressed: are student agents truly credible, and can they faithfully simulate human learning? In this study, we built a Big Five Personality-based student agent model with a full pipeline of student-teacher interaction, self-study, and examination. To evaluate behavioral fidelity, we collected 13 empirical studies on Big Five traits and learning, and distilled them into 14 criteria. We found that the 71.4% of the student agents' behavior was aligned with human learners.

Problem

• student agent
• behavioral fidelity
• Big Five Personality
• mathematics education
• LLM-based simulation

Innovation

• personality-driven agents
• LLM-based simulation
• behavioral fidelity
• Big Five personality
• student modeling