EZYer: A simulacrum of high school with generative agent

2025-12-02

AI Summary

Existing educational tools suffer from fragmented services, suboptimal performance, and weak interactivity in lecture material generation, interactive note-taking, and content quality assurance. To address these challenges, this paper proposes a multi-role generative agent collaboration framework for a high-school pedagogical simulation system, integrating four specialized agents—teacher, teaching assistant, high-performing student, and struggling student—coordinated via role-shared experience mechanisms and a dynamic error-correction system. Technically, the framework unifies text retrieval, deep generative modeling, automated LaTeX Beamer layout, keyword filtering, content scoring, and cross-model collaborative verification. Experimental evaluation of 100 generated lecture decks and notes demonstrates high accuracy, comprehensive knowledge coverage, and strong usability; five large language models independently confirm superior output quality. This work pioneers a multi-role generative agent collaboration paradigm tailored to instructional contexts, establishing a novel methodology and practical pathway for intelligent educational systems.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• 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: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

With the rapid development of the online education and large language model, the existing educational tools still suffer from incomplete service, insufficient performance and weak interactivity in terms of courseware generation, interactive notes and quality assurance of content. In particular, the proposed generative agent EZYer : 1) Teacher Module: Integrating the Text Corpus retrieval and in-depth generation technologies, it automatically generates structured teaching materials and LaTeX Beamer courseware in line with the high school mathematics syllabus and supports user-defined image insertion. 2) Student Module: Throughout the collaborative interaction of the four roles of Teacher, Assistant, Top Student and Struggling Student, Note Taker summarizes and generates academic notes to enhance the depth and interest of learning. 3) Controller: set up keyword filtering system, content scoring system, role co-validation system, and dynamic content correction system. This ensure academic strictness and pedagogical propriety of EZYer inputs and outputs. In order to evaluate EZYer, this paper designs five-dimensional evaluation indexes of content accuracy, knowledge coverage, usability, formatting correctness and visual design and appeal, and scores 100 Beamer and Notes generated by EZYer by five large language models, separately, and the results show that the quality of EZYer-generated content is excellent and has a good application prospect.

Problem

• Automates structured teaching material and LaTeX courseware generation for high school math
• Enhances learning depth and interest through multi-role collaborative note-taking
• Ensures academic strictness via filtering, scoring, and correction systems

Innovation

• Generative agent integrates retrieval and generation for structured teaching materials
• Four-role collaborative interaction enhances learning depth and interest
• Multi-system controller ensures academic strictness and pedagogical propriety