LectūraAgents：一种面向自适应个性化AI辅助学习与具身教学的多智能体框架

摘要

有效的个性化AI辅助学习要求系统不仅能生成精准适配学习者的教学内容，还需动态调整教学方式以适应多样化学习者。然而，现有教育智能体主要聚焦于讲座内容自动化与模拟，往往难以构建针对个体学习者的多模态具身教学模型。为此，我们提出LectūraAgents——一个通过端到端自适应具身教学实现个性化学习的多智能体框架。该框架的核心是模拟教授-学生关系：教授智能体（ProfessorAgent）领导一个由专业子智能体组成的协作团队，通过研究、规划、审核及具身化交付动态适配学习者需求的讲座内容。本框架做出三项主要贡献：（1）用于端到端个性化学习的层级化多智能体架构；（2）自适应具身教学机制——教授智能体在教学环境中执行可视化、具备教学动因的教学动作（如手写、高亮、下划线等）；（3）教学动作-语音对齐算法（TASA），该算法基于显著性启发式规则与时序语义分割，生成与学习者画像一致的教学动作序列。我们通过基于样本标准的细粒度评估，在高中、本科及研究生阶段的多样化课程中验证LectūraAgents性能；生成的讲座材料与教学动作经教育专家评估验证。实验结果表明，相比现有方法，本框架在讲座内容质量、具身教学质量、评估效果及个性化水平上均取得持续提升，为大规模个性化学习奠定了坚实教学理论基础。

English

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.