🧠 AI Ed Wiki

📄 Research Article

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

● high · 2026-06-17llm, generative-ai, personalized-learning, higher-ed, intelligent-tutoring, pedagogical-llm-training, rag

Jaward Sesay, Yue Yu, Siwei Dong, Yemin Shi, Guangyao Chen, Borje F. Karlsson (2026). arXiv cs.CL

Jaward Sesay, Yue Yu, Siwei Dong, Yemin Shi, Guangyao Chen, Borje F. Karlsson (2026). arXiv cs.CL

Key Findings

  • Hierarchical multi-agent framework (ProfessorAgent + subordinate agents) enables end-to-end adaptive embodied teaching.
  • TASA algorithm aligns teaching actions with learner profiles.
  • Outperforms baselines on lecture quality, embodiment, assessment, and personalization.
  • Given a lecture prompt or learning materials plus a learner profile, a ProfessorAgent leads a collaborative team of specialized agents through research, planning, design, evaluation, and embodied delivery of lecture and study content that adapts to the individual learner.
  • The framework provides students with access to real-time adaptive, personalized teaching and study sessions, addressing a gap in prior educational agent frameworks that focused mainly on lecture content automation and simulation.
  • Evaluation across high school, undergraduate, and graduate-level courses using sample-specific rubric-based analysis, with generated lecture materials and teaching actions assessed and validated by expert educators, shows consistent gains over existing approaches.

    • Architecture & Method

    At its core, LecturaAgents mirrors a professor–student relationship: a ProfessorAgent orchestrates specialized agents across the full teaching pipeline, from researching content to planning, designing, evaluating, and delivering instruction. Two mechanisms distinguish it from prior work. First, an adaptive embodied teaching mechanism lets the ProfessorAgent execute visible, pedagogically motivated teaching actions — handwriting, highlighting, underlining — over content in a teaching environment while speaking. Second, the Teaching Action-Speech Alignment (TASA) algorithm employs salience-based heuristics and temporal semantic segmentation to generate coherent teaching action sequences aligned with learner profiles. The multimodal, embodied dimension is what positions the framework as pedagogically grounded Personalized Learning rather than mere content generation.

    Relevance to AI in Education

    This paper contributes directly to understanding how AI systems interact with learners in authentic educational settings. It introduces hierarchical multi-agent architectures for embodied, personalized teaching that adapts lecture content and actions to individual learners, positioning LecturaAgents as a pedagogically well-grounded framework for personalized learning at scale. The expert-validated rubric evaluation across educational levels makes the framework relevant to Intelligent Tutoring and Pedagogical LLM Training research on embodied and multimodal instruction.

    Connected Concepts

  • Personalized Learning
  • Pedagogical LLM Training
  • Pedagogical Agent
  • Affective Computing
  • Lifelong Learning
  • Socratic Method
  • Affective Tutoring
  • Teacher AI Competency

    • Connected Articles

  • Retrieval Augmented Tutoring Algorithm Kite — Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education
  • Learning Engagement Assistant Lea — Learning Engagement Assistant (LEA): Cross-Course Scalability and Classroom Evaluation of an Agentic AI Tutoring System
  • Kt4eqg Personalized Question Generation — KT4EQG: Personalized Exercise Question Generation via Knowledge Tracing
  • AI LMS Middle School Longitudinal — AI-Integrated Learning Management System for Middle School: A Longitudinal Study of Learning Outcomes
  • Cognitive Agent Compilation — Cognitive Agent Compilation for Explicit Problem Solver Modeling
  • LLM Student Modeling Memory — LLM Student Modeling and Long-Term Memory Architecture

    • Citation

    Jaward Sesay, Yue Yu, Siwei Dong, Yemin Shi, Guangyao Chen, Borje F. Karlsson (2026). LecturaAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching. arXiv:2606.16428. arXiv cs.CL.