Multi-Agent Learning Path Planning via LLMs

TL;DR

This paper introduces a multi-agent framework using LLMs for personalized learning path planning, emphasizing transparency, adaptability, and pedagogical alignment in higher education.

Contribution

It proposes a novel collaborative multi-agent system leveraging LLMs, grounded in educational theories, to generate and refine personalized learning paths with interpretability.

Findings

Outperforms baseline models in path quality and coherence

Demonstrates effective collaboration among agents improves learning path relevance

Validates the approach across multiple LLMs and datasets

Abstract

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 by LLMs. The framework includes three task-specific agents: a learner analytics agent, a path planning agent, and a reflection agent. These agents collaborate via structured prompts and predefined rules to analyze learning profiles, generate tailored learning paths, and iteratively refine them with interpretable feedback. Grounded in Cognitive Load Theory and Zone of Proximal Development, the system ensures that recommended paths are cognitively aligned and pedagogically meaningful. Experiments conducted on the MOOCCubeX dataset using seven LLMs show that MALPP significantly outperforms baseline models in path quality, knowledge sequence consistency, and cognitive load alignment. Ablation studies further validate the effectiveness of the collaborative mechanism and theoretical constraints. This research contributes to the development of trustworthy, explainable AI in education and demonstrates a scalable approach to learner-centered adaptive instruction powered by LLMs.