RoboBuddy in the Classroom: Exploring LLM-Powered Social Robots for Storytelling in Learning and Integration Activities

2025-08-22

AI Summary

Contextualized instructional design for multicultural education is time-intensive and imposes high technical barriers on educators. Method: This study proposes an LLM-driven social robot teaching system featuring an intuitive human–robot interface, enabling teachers to rapidly generate and dynamically adapt culturally narrative-based situational activities from routine lesson plans. Contribution/Results: We report the first week-long, sustained deployment of an LLM-augmented social robot in authentic classroom settings (N=27). Results demonstrate statistically significant reductions in teacher preparation burden and significant improvements in student learning enjoyment (p<0.01) and positive attitudes toward integration policies. The system validates a novel paradigm for intercultural pedagogy characterized by low technical entry barriers, high interactivity, and deep emotional engagement. This work provides empirical evidence supporting the transition of educational robots from demonstration prototypes to routine classroom implementation.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Natural Language Processing: Safety and Robustness
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Creating and improvising scenarios for content approaching is an enriching technique in education. However, it comes with a significant increase in the time spent on its planning, which intensifies when using complex technologies, such as social robots. Furthermore, addressing multicultural integration is commonly embedded in regular activities due to the already tight curriculum. Addressing these issues with a single solution, we implemented an intuitive interface that allows teachers to create scenario-based activities from their regular curriculum using LLMs and social robots. We co-designed different frameworks of activities with 4 teachers and deployed it in a study with 27 students for 1 week. Beyond validating the system's efficacy, our findings highlight the positive impact of integration policies perceived by the children and demonstrate the importance of scenario-based activities in students' enjoyment, observed to be significantly higher when applying storytelling. Additionally, several implications of using LLMs and social robots in long-term classroom activities are discussed.

Problem

• Reducing planning time for scenario-based educational activities
• Integrating multicultural content into tight curriculum schedules
• Enhancing student engagement through storytelling with social robots

Innovation

• LLM-powered social robots for storytelling
• Intuitive interface for curriculum-based scenarios
• Co-designed frameworks with teachers for integration