mlsanityData to 7 Oct 2026

SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice

arXiv 2606.04155 ↗First posted 2 Jun 2026cs.HC cs.CL cs.CYcited by 0

On the map: LLM agents and tool use → Educational agents and math problem solving

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

20 of 49 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment7 Jul
  2. 2025LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System27 Jan

Other references · 18

  1. 2024A Survey on LLM-as-a-Judgecited by 1,384
  2. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  3. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  4. 2025Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Librarycited by 94
  5. 2024Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categoriescited by 74
  6. 2023Rehearsal: Simulating Conflict to Teach Conflict Resolutioncited by 54
  7. 2024User Modeling and User Profiling: A Comprehensive Surveycited by 29
  8. 2024GPTCoach: Towards LLM-Based Physical Activity Coachingcited by 29
  9. 2024Learning Retrieval Augmentation for Personalized Dialogue Generationcited by 18
  10. 2026ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Rankingcited by 17
  11. 2025Scaffolding Empathy: Training Counselors with Simulated Patients and Utterance-level Performance Visualizationscited by 14
  12. 2021Personalized Education in the AI Era: What to Expect Next?cited by 13
6 more
  1. 2025Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrievalcited by 11
  2. 2024Education in the Era of Neurosymbolic AIcited by 4
  3. 2025An LLM-Guided Tutoring System for Social Skills Trainingcited by 4
  4. 2025PlanGlow: Personalized Study Planning with an Explainable and Controllable LLM-Driven Systemcited by 3
  5. 2026DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agentscited by 2
  6. 2024Modeling Balanced Explicit and Implicit Relations with Contrastive Learning for Knowledge Concept Recommendation in MOOCscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DeepTutor: Towards Agentic Personalized Tutoring
  2. 2025IntelliCode: A Multi-Agent LLM Tutoring System with Centralized Learner Modeling
  3. 2026EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners
  4. 2026From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
  5. 2025Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning
  6. 2025LOOM: Personalized Learning Informed by Daily LLM Conversations Toward Long-Term Mastery via a Dynamic Learner Memory Graph
  7. 2026PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering
  8. 2025Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems