SocialWise: LLM-Agentic Conversation Therapy for Individuals with Autism Spectrum Disorder to Enhance Communication Skills

arXiv:2604.15347v1 Announce Type: cross Abstract: Autism Spectrum Disorder (ASD) affects more than 75 million people worldwide. However, scalable support for practicing everyday conversation is scarce: Low-cost activities such as story reading yield limited improvement. At the same time, effective role-play therapy demands expensive, in-person sessions with specialists. SocialWise bridges this gap through a browser-based application that pairs LLM conversational agents with a therapeutic retrieval augmented generation (RAG) knowledge base. Users select a scenario (e.g., ordering food, joining a group), interact by text or voice, and receive instant, structured feedback on tone, engagement, and alternative phrasing. The SocialWise prototype, implemented with Streamlit, LangChain, and ChromaDB, runs on any computer with internet access, and demonstrates how recent advances in LLM can provide evidence-based, on-demand communication coaching for individuals with ASD.

Related

• ACE-TA: An Agentic Teaching Assistant for Grounded Q&A, Quiz Generation, and Code Tutoring
• Young people's perceptions and recommendations for conversational generative artificial intelligence in youth mental health
• Computer Environments Elicit General Agentic Intelligence in LLMs
• Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition

Source: arXiv cs.AI | 2026-04-20