Date
AI Overview
Why it matters
Online educational tools often lack complete services, strong interactivity, and quality assurance, particularly in generating structured presentations and interactive study notes.
Study at a glance
- Question: Can a multi-agent system effectively simulate classroom interactions to generate high school math presentations and study notes?
- Setting and data: High school mathematics curriculum context; 100 system-generated presentation slides and study notes documents.
- Method: System development and automated evaluation across five dimensions using five large language models.
- AI tools: EZYer, DeepSeek-V3, ChatGPT-o1, Claude 3.5 Sonnet, Gemini-2.0-Pro, Qwen2.5-Max
Key findings
- Evaluated by five models, generated presentations and notes scored highest in content accuracy and knowledge coverage, averaging around 4.7 out of 5.
- Formatting correctness achieved a high mean score of 4.35 for presentations, confirming reliable compiling into LaTeX and PDF formats.
- Usability and visual design received comparatively lower scores, with average ratings falling as low as 4.1 out of 5.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
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.
Research Categories
What is the application?
Who age?
Study design
Publication Source
Publisher
arXiv
