SocialCoach: Personalized Social Skill Learning with RL-based Agentic Tutoring and Practice

2026-06-02

AI Summary

This work addresses the scarcity of expert coaches and the lack of scalable, personalized approaches in social skills training by proposing EQoach, an intelligent tutoring system grounded in large language models. EQoach integrates a theoretically informed, practice-oriented pedagogical knowledge base constructed through multi-agent collaboration, and employs a causality-driven competency assessment, a reflective coaching mechanism, and a reinforcement learning–based adaptive exercise scheduler within an immersive, goal-directed environment to enable efficient skill acquisition. Notably, it pioneers the application of reinforcement learning to tackle both cold-start and long-term optimization challenges in social skills training. Deployment results demonstrate significant improvements in simulated learning trajectory quality and expert-rated performance, with user feedback indicating high engagement and perceived practical utility.

Abstract

Social skills such as negotiation and leadership are crucial for personal and professional success in today's interconnected world. However, scalable and effective training remains a significant challenge due to the scarcity of expert coaching. In this paper, we introduce SocialCoach, a holistic LLM-powered agentic tutoring system for personalized social skill development at scale. First, SocialCoach automatically constructs a pedagogically-grounded, theory-to-practice knowledge corpus from diverse expert sources, leveraging a multi-agent pipeline. Second, to personalize the learning journey, it employs an adaptive practice scheduling module that follows a prescription-retrieval-adaptation process. To maximize the long-term learning experience while overcoming the cold-start problem, this policy is optimized within a learner simulation environment through reinforcement learning. Finally, SocialCoach integrates immersive, goal-driven practice, causality-driven proficiency assessment and knowledge-grounded, reflective tutoring to help address the knowing-doing gap. We deploy it in our product, EQoach, and conduct extensive experiments. The results show that SocialCoach improves simulated pathway quality and judge-rated tutoring quality over baseline approaches, while early user feedback indicates strong perceived engagement and usefulness. These findings suggest a practical architecture for personalized and gamified pedagogical platforms on soft skill learning.

Problem

• social skills
• personalized learning
• scalable training
• expert coaching scarcity
• soft skill development

Innovation

• reinforcement learning
• agentic tutoring
• personalized practice scheduling
• theory-to-practice knowledge corpus
• causality-driven assessment