Multi-Agent Learning Path Planning via LLMs

This paper proposes a Multi-Agent Learning Path Planning (MALPP) framework using LLMs to generate personalized learning paths in higher education, specifically tested on MOOC data. The system uses three collaborative agents (learner analytics, path planning, and reflection) grounded in Cognitive Load Theory and Zone of Proximal Development to recommend pedagogically aligned learning sequences.

The integration of large language models (LLMs) into intelligent tutoring systems offers transformative potential for personalized learning in higher education. However, most existing learning path planning approaches lack transparency, adaptability, and learner-centered explainability. To address these challenges, this study proposes a novel Multi-Agent Learning Path Planning (MALPP) framework that leverages a role- and rule-based collaboration mechanism among intelligent agents, each powered b

Study Type

Source

Framework Categories

Tool Types

Tags