Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems

2025-01-17

AI Summary

To address the fidelity gap in simulating online learner behaviors and the significant discrepancy between offline evaluation and real-world online performance in personalized learning systems, this paper proposes a generative learner agent framework powered by large language models (LLMs). The framework innovatively integrates learner profiling, a psychology-inspired memory module, and a multi-behavior action module, enabling closed-loop interaction with adaptive testing algorithms such as computerized adaptive testing (CAT). Compared to conventional approaches, our agent substantially improves the authenticity and diversity of generated learning responses—better capturing real learner distributions across critical dimensions including response timing, strategy selection, and error patterns. All code and data are publicly released. This work establishes a new paradigm for trustworthy simulation and rigorous algorithm validation in educational AI.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Personalized learning represents a promising educational strategy within intelligent educational systems, aiming to enhance learners' practice efficiency. However, the discrepancy between offline metrics and online performance significantly impedes their progress. To address this challenge, we introduce Agent4Edu, a novel personalized learning simulator leveraging recent advancements in human intelligence through large language models (LLMs). Agent4Edu features LLM-powered generative agents equipped with learner profile, memory, and action modules tailored to personalized learning algorithms. The learner profiles are initialized using real-world response data, capturing practice styles and cognitive factors. Inspired by human psychology theory, the memory module records practice facts and high-level summaries, integrating reflection mechanisms. The action module supports various behaviors, including exercise understanding, analysis, and response generation. Each agent can interact with personalized learning algorithms, such as computerized adaptive testing, enabling a multifaceted evaluation and enhancement of customized services. Through a comprehensive assessment, we explore the strengths and weaknesses of Agent4Edu, emphasizing the consistency and discrepancies in responses between agents and human learners. The code, data, and appendix are publicly available at https://github.com/bigdata-ustc/Agent4Edu.

Problem

• Personalized Learning Systems
• Online Learning Efficiency
• Quality Improvement

Innovation

• Agent4Edu
• Personalized Learning
• Intelligent Agents