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

AgentTutor is a multi-turn interactive intelligent education system powered by LLM-based generative agents that provides personalized learning through five key modules: curriculum decomposition, learner assessment, dynamic teaching strategy adjustment, teaching reflection, and knowledge memory. The system evaluates learners' cognitive levels using Bloom's Taxonomy, dynamically adapts teaching strategies based on real-time feedback, and was tested on multiple benchmark datasets to demonstrate effectiveness in multi-turn interactions and teaching quality.

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-tur

Study Type

Source

Framework Categories

Tool Types

Tags