LecturaRaagents: A Multi-Agent Framework For Adaptive Personalized AI-Assisted Learning And Embodied Teaching

Jaward Sesay, Beijing Institute of Technology

Yue Yu, Beijing Institute of Technology

Siwei Dong, Peking University

Guangyao Chen

Börje F. Karlsson, Beijing Academy of Artificial Intelligence

Date

06/2026

AI Overview

Why it matters

Personalized learning requires dynamically adapting instruction to individual students, yet existing educational agents focus primarily on lecture automation and simulations rather than multimodal, embodied teaching methods.

Study at a glance

Question: Can a multi-agent framework improve personalized learning by dynamically adapting embodied teaching actions to individual students?
Setting and data: High school, undergraduate, and graduate courses evaluated by expert educators using sample-specific rubrics.
Method: System development and prototype evaluation using sample-specific rubric assessments by expert educators.
AI tools: LecturaAgents

Key findings

The new multi-agent system consistently outperformed existing approaches in lecture content quality, embodied teaching quality, assessment, and personalization across high school, undergraduate, and graduate courses.
A hierarchical multi-agent structure successfully simulated a professor-student relationship to plan, review, and deliver personalized educational content.
A specialized alignment algorithm effectively generated coherent sequences of visible teaching actions, such as handwriting and highlighting, that matched learner profiles.

Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.

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 Lect≈´raAgents - a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching. At its core, Lect≈´raAgents 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 Lect≈´raAgents 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 Lect≈´raAgents as a pedagogically well-grounded framework for personalized learning at scale.