AgentSME for Simulating Diverse Communication Modes in Smart Education

TL;DR

This paper introduces AgentSME, a generative agent framework for smart education that models diverse communication modes using LLMs, demonstrating improved accuracy and diversity in educational interactions.

Contribution

It proposes a unified LLM-based framework with three communication modes, evaluating their effectiveness in simulating human-like educational interactions.

Findings

Echo mode achieves highest accuracy

DeepSeek exhibits greatest diversity

Robustness across different LLM tiers

Abstract

Generative agent models specifically tailored for smart education are critical, yet remain relatively underdeveloped. A key challenge stems from the inherent complexity of educational contexts: learners are human beings with various cognitive behaviors, and pedagogy is fundamentally centered on personalized human-to-human communication. To address this issue, this paper proposes AgentSME, a unified generative agent framework powered by LLM. Three directional communication modes are considered in the models, namely Solo, Mono, and Echo, reflecting different types of agency autonomy and communicative reciprocity. Accuracy is adopted as the primary evaluation metric, complemented by three diversity indices designed to assess the diversity of reasoning contents. Six widely used LLMs are tested to validate the robustness of communication modes across different model tiers, which are equally divided into base-capacity and high-capacity configurations. The results show that generative agents that employ the Echo communication mode achieve the highest accuracy scores, while DeepSeek exhibits the greatest diversity. This study provides valuable information to improve agent learning capabilities and inspire smart education models.