Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems

Yuxin Liu, Zeqing Song, Jiong Lou, Chentao Wu, Jie Li

TL;DR

AgentTutor is a multi-turn interactive intelligent education system that dynamically optimizes and delivers teaching strategies based on learners' learning status, personalized goals, learning preferences, and multimodal study materials that significantly enhances learners' performance while demonstrating strong effectiveness in multi-turn interactions and competitiveness in teaching quality among other baselines.

Abstract

The rapid advancement of large-scale language models (LLMs) has shown their potential to transform intelligent education systems (IESs) through automated teaching and learning support applications. However, current IESs often rely on single-turn static question-answering, which fails to assess learners' cognitive levels, cannot adjust teaching strategies based on real-time feedback, and is limited to providing simple one-off responses. To address these issues, we introduce AgentTutor, a multi-turn interactive intelligent education system to empower personalized learning. It features an LLM-powered generative multi-agent system and a learner-specific personalized learning profile environment that dynamically optimizes and delivers teaching strategies based on learners' learning status, personalized goals, learning preferences, and multimodal study materials. It includes five key modules: curriculum decomposition, learner assessment, dynamic strategy, teaching reflection, and knowledge & experience memory. We conducted extensive experiments on multiple benchmark datasets, AgentTutor significantly enhances learners' performance while demonstrating strong effectiveness in multi-turn interactions and competitiveness in teaching quality among other baselines.

AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems

TL;DR

AgentTutor is a multi-turn interactive intelligent education system that dynamically optimizes and delivers teaching strategies based on learners' learning status, personalized goals, learning preferences, and multimodal study materials that significantly enhances learners' performance while demonstrating strong effectiveness in multi-turn interactions and competitiveness in teaching quality among other baselines.

Abstract

The rapid advancement of large-scale language models (LLMs) has shown their potential to transform intelligent education systems (IESs) through automated teaching and learning support applications. However, current IESs often rely on single-turn static question-answering, which fails to assess learners' cognitive levels, cannot adjust teaching strategies based on real-time feedback, and is limited to providing simple one-off responses. To address these issues, we introduce AgentTutor, a multi-turn interactive intelligent education system to empower personalized learning. It features an LLM-powered generative multi-agent system and a learner-specific personalized learning profile environment that dynamically optimizes and delivers teaching strategies based on learners' learning status, personalized goals, learning preferences, and multimodal study materials. It includes five key modules: curriculum decomposition, learner assessment, dynamic strategy, teaching reflection, and knowledge & experience memory. We conducted extensive experiments on multiple benchmark datasets, AgentTutor significantly enhances learners' performance while demonstrating strong effectiveness in multi-turn interactions and competitiveness in teaching quality among other baselines.
Paper Structure (32 sections, 5 figures, 10 tables, 1 algorithm)

This paper contains 32 sections, 5 figures, 10 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Intelligent Education Systems
  4. LLM-powered Agent Systems
  5. AgentTutor
  6. Problem Formulation
  7. LLM-powered AgentTutor
  8. Curriculum Decomposition Module (CDM).
  9. Learner Assessment Module (LAM).
  10. Dynamic Strategy Module (DSM).
  11. Teaching Reflection Module (TRM).
  12. Knowledge & Experience Memory Module (KEMM).
  13. Learner Profile Environment.
  14. Experiments
  15. Datasets.
  16. ...and 17 more sections

Figures (5)

  • Figure 1: A comparative analysis of existing systems and proposed AgentTutor. AgentTutor incorporates multiple LLM-powered generative agents along with a personalized environment to facilitate learning contexts.
  • Figure 2: The diagram highlights the multi-turn interaction framework of the AgentTutor system, showing the collaboration among the five modules and personalized learning profile environment, forming a dynamic process that enhances teaching effectiveness. We take the KNN (K-Nearest Neighbors) algorithm as the curriculum example.
  • Figure 3: Illustrating how the curriculum decomposition module decomposes a high-level curriculum, such as the KNN algorithm, into manageable sub-goals based on Bloom's Taxonomy. Leveraging educational theories, this module constructs a hierarchical tree that organizes these sub-goals into a structured learning pathway.
  • Figure 4: Comparison of interactive teaching quality across multi-turn interactions by conversational adaptability, feedback quality, and question difficulty.
  • Figure 5: Human evaluation of various teaching methods based on accuracy, conversational quality, helpfulness, and question set quality. AgentTutor demonstrates the highest performance across all criteria.