Personality-Driven Student Agent-Based Modeling in Mathematics Education: How Well Do Student Agents Align with Human Learners?
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917356726386688 |
|---|---|
| author | Xiao, Bushi Shen, Qian |
| author_facet | Xiao, Bushi Shen, Qian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21358 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Personality-Driven Student Agent-Based Modeling in Mathematics Education: How Well Do Student Agents Align with Human Learners? Xiao, Bushi Shen, Qian Multiagent Systems Computers and Society 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. |
| title | Personality-Driven Student Agent-Based Modeling in Mathematics Education: How Well Do Student Agents Align with Human Learners? |
| topic | Multiagent Systems Computers and Society |
| url | https://arxiv.org/abs/2603.21358 |