# SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice

arXiv: https://arxiv.org/abs/2606.04155 · HTML: https://mlsanity.com/paper/2606.04155/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 20 of 20)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library](https://mlsanity.com/paper/2506.06122/) (2025)
- [Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories](https://mlsanity.com/paper/2406.00034/) (2024)
- [Rehearsal: Simulating Conflict to Teach Conflict Resolution](https://mlsanity.com/paper/2309.12309/) (2023)
- [User Modeling and User Profiling: A Comprehensive Survey](https://mlsanity.com/paper/2402.09660/) (2024)
- [GPTCoach: Towards LLM-Based Physical Activity Coaching](https://mlsanity.com/paper/2405.06061/) (2024)
- [LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System](https://mlsanity.com/paper/2501.15749/) (2025)
- [Learning Retrieval Augmentation for Personalized Dialogue Generation](https://mlsanity.com/paper/2406.18847/) (2024)
- [ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking](https://mlsanity.com/paper/2601.06487/) (2026)
- [Scaffolding Empathy: Training Counselors with Simulated Patients and Utterance-level Performance Visualizations](https://mlsanity.com/paper/2502.18673/) (2025)
- [Personalized Education in the AI Era: What to Expect Next?](https://mlsanity.com/paper/2101.10074/) (2021)
- [Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval](https://mlsanity.com/paper/2510.08935/) (2025)
- [Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment](https://mlsanity.com/paper/2507.05528/) (2025)
- [Education in the Era of Neurosymbolic AI](https://mlsanity.com/paper/2411.12763/) (2024)
- [An LLM-Guided Tutoring System for Social Skills Training](https://mlsanity.com/paper/2501.09870/) (2025)
- [PlanGlow: Personalized Study Planning with an Explainable and Controllable LLM-Driven System](https://mlsanity.com/paper/2504.12452/) (2025)
- [DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents](https://mlsanity.com/paper/2605.29256/) (2026)
- [Modeling Balanced Explicit and Implicit Relations with Contrastive Learning for Knowledge Concept Recommendation in MOOCs](https://mlsanity.com/paper/2402.08256/) (2024)

## Abstract (arXiv)

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 work, we introduce SocialCoach, an LLM-powered agentic tutoring system for personalized social skill learning. SocialCoach constructs a theory-to-practice corpus of traceable strategies, cases, and practice scenarios, and uses this corpus for both scheduling and reflective tutoring. We formulate social practice personalization as cold-start, retrieval-constrained sequential practice scheduling. Given a learner profile, simulated proficiency state, and observed practice history, a policy produces structured prescriptions that are realized through corpus retrieval. To enhance scheduling effectiveness, we optimize complete pathways with trajectory-level GRPO using rubric-judge based pairwise preferences. Additionally, we instantiate the scheduling approach in a deployed platform with goal-driven practice and knowledge-grounded reflective tutoring. Finally, in the synthetic cold-start setting, experiment results show that SocialCoach achieves higher pathway-quality ratings than baselines in scheduling and tutoring quality. We also conduct human studies to demonstrate its usefulness for real-world social skill learning.