Personality-Driven Student Agent-Based Modeling in Mathematics Education: How Well Do Student Agents Align with Human Learners?
This addresses the need for ethical alternatives to real-person experiments in educational research, though it is incremental in validating agent fidelity.
The study tackled the problem of evaluating whether student agents based on Big Five Personality traits can credibly simulate human learning in mathematics education, finding that 71.4% of the agents' behavior aligned with human learners.
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.