EduPlanner: LLM-Based Multiagent Systems for Customized and Intelligent Instructional Design

EduPlanner is an LLM-based multi-agent system that automatically generates customized instructional designs (lesson plans) for mathematics education by modeling student knowledge using a Skill-Tree structure and iteratively optimizing content through adversarial collaboration between evaluator and optimizer agents. The system is evaluated on GSM8K and Algebra datasets using a five-dimensional assessment framework (CIDDP) measuring Clarity, Integrity, Depth, Practicality, and Pertinence of lesson plans.

Large language models (LLMs) have significantly advanced smart education in the artificial general intelligence era. A promising application lies in the automatic generalization of instructional design for curriculum and learning activities, focusing on two key aspects: 1) customized generation: generating niche-targeted teaching content based on students' varying learning abilities and states and 2) intelligent optimization: iteratively optimizing content based on feedback from learning effecti

Study Type

Source

Framework Categories

Tool Types

Tags