Multi-Agent Learning Path Planning via LLMs

2026-01-24

AI Summary

This work proposes a novel multi-agent collaborative framework for adaptive learning path planning that addresses the prevalent limitations of low transparency, weak adaptability, and insufficient learner-centered explainability in existing approaches. By integrating role- and rule-driven mechanisms with cognitive load theory and the zone of proximal development, the framework employs three specialized LLM-powered agents—learner analyzer, path planner, and reflector—that collaboratively generate and iteratively refine personalized learning paths. Experimental evaluation on the MOOCCubeX dataset demonstrates that the proposed method significantly outperforms baseline models in terms of path quality, knowledge sequence coherence, and alignment with cognitive load principles. Ablation studies further confirm the effectiveness of both the multi-agent collaboration architecture and the theoretical constraints embedded within the system.

Technology Category

• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Motion and Path Planning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• learning path planning
• explainability
• adaptability
• transparency
• intelligent tutoring systems

Innovation

• Multi-Agent System
• Large Language Models
• Learning Path Planning
• Explainable AI
• Cognitive Load Theory