Date
Publisher
arXiv
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.
Study at a glance
- Question: How do different communication styles affect how well AI agents perform and reason in educational settings?
- Setting and data: Six widely used large language models across base-capacity and high-capacity configurations.
- Method: Automated testing of six AI models across three communication modes to evaluate accuracy and reasoning diversity.
Why it matters
Generative agent models specifically tailored for smart education are critical yet remain relatively underdeveloped. Educational contexts are inherently complex, as learners have various cognitive behaviors and pedagogy is fundamentally centered on personalized human-to-human communication.
Key findings
- Generative AI agents achieved the highest accuracy scores when using Echo, a two-way reciprocal communication mode.
- The DeepSeek language model demonstrated the greatest diversity in its reasoning content among the tested AI tools.
- Educational AI tools remain relatively underdeveloped because human learning relies heavily on personalized communication and diverse cognitive behaviors.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
