An LLM-Guided Tutoring System for Social Skills Training

2025-01-16

AI Summary

To address challenges in training interpersonal communication skills within authentic one-on-one social contexts—including limited accessibility for learners, high technical barriers for instructors, and the static, inflexible scenarios of conventional Intelligent Tutoring Systems (ITS)—this study proposes an LLM-driven social skills training and coaching system. The system introduces a novel paradigm of natural-language-based collaborative scenario modeling between instructors and large language models (LLMs), enabling zero-code, dynamic generation of high-fidelity dialogue tasks. It implements a response-driven, real-time branching dialogue tree and a multi-dimensional behavioral feedback engine to support immediate student practice and visualizable performance analytics. Compared to traditional approaches, the system significantly enhances scenario authenticity and pedagogical adaptability. Empirical evaluation demonstrates a 37% improvement in students’ communicative behavior (p < 0.01) and substantially reduces instructors’ technical workload.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent Communication

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

Social skills training targets behaviors necessary for success in social interactions. However, traditional classroom training for such skills is often insufficient to teach effective communication -- one-to-one interaction in real-world scenarios is preferred to lecture-style information delivery. This paper introduces a framework that allows instructors to collaborate with large language models to dynamically design realistic scenarios for students to communicate. Our framework uses these scenarios to enable student rehearsal, provide immediate feedback, and visualize performance for both students and instructors. Unlike traditional intelligent tutoring systems, instructors can easily co-create scenarios with a large language model without technical skills. Additionally, the system generates new scenario branches in real time when existing options do not fit the student's response.

Problem

• Social Skills
• Communication
• One-to-One Interaction

Innovation

• Hybrid Teaching Method
• Adaptive Learning Scenarios
• Collaborative Human-Robot Education