EduAgent: Generative Student Agents in Learning

TL;DR

EduAgent introduces a novel generative framework using large language models and cognitive prior knowledge to simulate diverse student behaviors in online education, outperforming existing models in realism and prediction accuracy.

Contribution

This work presents EduAgent, a new generative student agent framework that incorporates cognitive science knowledge to improve simulation of student behaviors using LLMs.

Findings

EduAgent accurately predicts real student behaviors.

It can generate realistic virtual student behaviors without real data.

Outperforms existing simulation models in educational contexts.

Abstract

Student simulation in online education is important to address dynamic learning behaviors of students with diverse backgrounds. Existing simulation models based on deep learning usually need massive training data, lacking prior knowledge in educational contexts. Large language models (LLMs) may contain such prior knowledge since they are pre-trained from a large corpus. However, because student behaviors are dynamic and multifaceted with individual differences, directly prompting LLMs is not robust nor accurate enough to capture fine-grained interactions among diverse student personas, learning behaviors, and learning outcomes. This work tackles this problem by presenting a newly annotated fine-grained large-scale dataset and proposing EduAgent, a novel generative agent framework incorporating cognitive prior knowledge (i.e., theoretical findings revealed in cognitive science) to guide LLMs to first reason correlations among various behaviors and then make simulations. Our two experiments show that EduAgent could not only mimic and predict learning behaviors of real students but also generate realistic learning behaviors of virtual students without real data.