Search and Filter

Llm Agents For Education: Advances And Applications

Date

AI Overview

Why it matters

Traditional educational data mining tools struggle with shallow context, limited interactivity, and rigid content generation. Large language model agents provide memory, tool use, and planning that could automate complex pedagogical tasks and personalize instruction.

Study at a glance
  • Question: How are large language model agents currently used to support teaching and learning, and what challenges do they face?
  • Setting and data: Google Scholar search of studies published between 2020 and May 2025 on educational AI agents.
  • Method: Systematic literature review (systematic review)
  • AI tools: GPT-4, TourSynbio-7B
Key findings
  • Educational agents primarily serve two roles: teaching assistance (classroom simulation, feedback generation, and curriculum design) and student support (adaptive learning, knowledge tracing, and error detection).
  • Effective educational agents rely on core abilities including short- and long-term memory, external tool use, goal planning, explainability, personalization, and multi-agent collaboration.
  • Real-world educational deployment remains limited by significant challenges surrounding data privacy, algorithmic bias, hallucination, student overreliance, and integration into existing school ecosystems.

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

Large Language Model (LLM) agents are transforming education by automating complex pedagogical tasks and enhancing both teaching and learning processes. In this survey, we present a systematic review of recent advances in applying LLM agents to address key challenges in educational settings, such as feedback comment generation, curriculum design, etc. We analyze the technologies enabling these agents, including representative datasets, benchmarks, and algorithmic frameworks. Additionally, we highlight key challenges in deploying LLM agents in educational settings, including ethical issues, hallucination and overreliance, and integration with existing educational ecosystems. Beyond the core technical focus, we include in Appendix A a comprehensive overview of domain-specific educational agents, covering areas such as science learning, language learning, and professional development.