A Scoping Review of Large Language Model-Based Pedagogical Agents
Summary: arXiv:2604.12253v1 Announce Type: new
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.
Key Findings
Our analysis highlighted four key design dimensions that characterize LLM-based pedagogical agents:
- Interaction Approach: Agents can be either reactive or proactive in their interactions with learners.
- Domain Scope: Agents may be domain-specific, targeting particular subjects, or general-purpose, applicable across various disciplines.
- Role Complexity: Some agents function in a single role, while others take on multiple roles to enrich the learning experience.
- System Integration: Agents can operate as standalone systems or be integrated into existing educational frameworks.
Emerging Trends
The review also identified several emerging trends in the use of LLM-based pedagogical agents:
- Development of multi-agent systems that mimic naturalistic learning environments.
- Utilization of virtual student simulations for evaluating agent effectiveness.
- Integration with immersive technologies, such as virtual and augmented reality.
- Combining LLMs with learning analytics to enhance personalized learning pathways.
Research Gaps and Ethical Considerations
Despite the promising developments, significant research gaps remain. Ethical considerations, particularly regarding privacy, accuracy, and student autonomy, must be addressed to ensure the responsible implementation of these technologies.
This scoping review provides researchers and practitioners with a comprehensive understanding of LLM-based pedagogical agents, while also identifying crucial areas for future development in this rapidly evolving field.