A Scoping Review of Large Language Model-Based Pedagogical Agents

2026-04-13

AI Summary

This study addresses the current lack of a systematic synthesis regarding the application, design patterns, and research gaps of large language model (LLM)-driven pedagogical agents in education. Following the PRISMA-ScR guidelines, the authors conducted a scoping review of 52 studies published between November 2022 and January 2025, integrating literature from five major databases through bibliometric and qualitative analyses. They propose an innovative four-dimensional design framework—encompassing interaction modality, domain scope, role complexity, and system integration—to elucidate the distinctive deployment characteristics of such agents across K–12, higher education, and informal learning contexts. The review also identifies emerging trends, including multi-agent systems, virtual student simulation, and integration with immersive technologies, while highlighting critical ethical challenges related to privacy, content accuracy, and learner autonomy, thereby charting directions for future research.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Multiagent Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

This scoping review examines the emerging field of Large Language Model (LLM)-based pedagogical agents in educational settings. While traditional pedagogical agents have been extensively studied, the integration of LLMs represents a transformative advancement with unprecedented capabilities in natural language understanding, reasoning, and adaptation. Following PRISMA-ScR guidelines, we analyzed 52 studies across five major databases from November 2022 to January 2025. Our findings reveal diverse LLM-based agents spanning K-12, higher education, and informal learning contexts across multiple subject domains. We identified four key design dimensions characterizing these agents: interaction approach (reactive vs. proactive), domain scope (domain-specific vs. general-purpose), role complexity (single-role vs. multi-role), and system integration (standalone vs. integrated). Emerging trends include multi-agent systems that simulate naturalistic learning environments, virtual student simulation for agent evaluation, integration with immersive technologies, and combinations with learning analytics. We also discuss significant research gaps and ethical considerations regarding privacy, accuracy, and student autonomy. This review provides researchers and practitioners with a comprehensive understanding of LLM-based pedagogical agents while identifying crucial areas for future development in this rapidly evolving field.

Problem

• Large Language Models
• Pedagogical Agents
• Educational Technology
• Scoping Review
• AI in Education

Innovation

• Large Language Models
• Pedagogical Agents
• Multi-agent Systems
• Learning Analytics
• Immersive Technologies