NeuroWise: A Multi-Agent LLM "Glass-Box" System for Practicing Double-Empathy Communication with Autistic Partners

2026-02-21

AI Summary

This study addresses communication barriers between neurodivergent and neurotypical individuals arising from the “double empathy problem” by moving beyond traditional interventions that focus solely on autistic individuals. It proposes the first AI-assisted communication system grounded in a bidirectional understanding framework. Built upon an interpretable “glass-box” multi-agent large language model architecture, the system integrates stress visualization, interpretation of internal experiences, and context-aware guidance to enhance neurotypical users’ comprehension of and empathy toward their autistic partners. Experimental results demonstrate that the system significantly reduces deficit-based attributions toward autism (p = 0.02) and improves conversational efficiency by 37% (p = 0.03). All participants affirmed its effectiveness, marking a shift in communication support from unidirectional correction toward mutual, reciprocal understanding.

Technology Category

• Humans and AI: AI for Accessibility
• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The double empathy problem frames communication difficulties between neurodivergent and neurotypical individuals as arising from mutual misunderstanding, yet most interventions focus on autistic individuals. We present NeuroWise, a multi-agent LLM-based coaching system that supports neurotypical users through stress visualization, interpretation of internal experiences, and contextual guidance. In a between-subjects study (N=30), NeuroWise was rated as helpful by all participants and showed a significant condition-time effect on deficit-based attributions (p=0.02): NeuroWise users reduced deficit framing, while baseline users shifted toward blaming autistic "deficits" after difficult interactions. NeuroWise users also completed conversations more efficiently (37% fewer turns, p=0.03). These findings suggest that AI-based interpretation can support attributional change by helping users recognize communication challenges as mutual.

Problem

• double empathy problem
• neurodivergent
• neurotypical
• communication difficulties
• mutual misunderstanding

Innovation

• multi-agent LLM
• double empathy
• glass-box system
• attributional change
• neurodiversity