LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

2026-06-15

AI Summary

This study addresses the challenge that existing educational agents struggle to deliver truly personalized instruction that is multimodal, embodied, and dynamically adaptive to individual learners. To overcome this limitation, the authors propose a hierarchical multi-agent framework that simulates professor–student interactions through collaborative mechanisms—including research, planning, review, and embodied lecturing—to enable end-to-end adaptive teaching. Key innovations include embodied instructional action execution (e.g., handwriting and highlighting) and a Teaching Action–Speech Alignment (TASA) algorithm, which integrates saliency-based heuristics with temporal semantic segmentation to generate coherent teaching behavior sequences aligned with the learner’s profile. Experimental results across high school to graduate-level courses demonstrate significant improvements in lecture quality, embodied expressiveness, assessment outcomes, and personalization, with validation from domain experts in education.

Abstract

Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing educational agents have primarily focused on lecture content automation and simulations, which often fall short of modelling multimodal and embodied instructional methods tailored for the individual learner. To this end, we propose LectūraAgents - a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching. At its core, LectūraAgents mirrors a professor-student relationship, in which a ProfessorAgent leads a collaborative team of specialized subordinate agents through research, planning, review, and embodied delivery of lecture contents that adapt to a learner's needs. The framework offers three main contributions: (1) a hierarchical multi-agent architecture for end-to-end personalized learning; (2) an adaptive embodied teaching mechanism, wherein the ProfessorAgent executes visible and pedagogically motivated teaching actions (e.g., handwrite, highlight, underline, etc.) over contents in a teaching environment; and (3) a Teaching Action-Speech Alignment (TASA) algorithm that employs salience-based heuristics and temporal semantic segmentation to generate coherent teaching action sequences aligned with learner profiles. We evaluate LectūraAgents on diverse courses at high school, undergraduate, and graduate levels using sample-specific rubric-based analysis; with generated lecture materials and teaching actions assessed and validated by expert educators. Experimental results show consistent gains in lecture content quality, embodied teaching quality, assessment, and personalization over existing approaches, positioning LectūraAgents as a pedagogically well-grounded framework for personalized learning at scale.

Problem

• personalized learning
• embodied teaching
• multi-agent framework
• adaptive instruction
• AI-assisted education

Innovation

• multi-agent framework
• embodied teaching
• adaptive personalization
• Teaching Action-Speech Alignment
• hierarchical agent architecture