"Listen, Who is Anxious?": A Multi-Agent Coordination and Self-Dialogue Mechanism Based on Internal Family Systems Theory
Abstract
As AI increasingly becomes a "digital tree hole" for emotional expression, existing tools remain limited by their lack of theoretical grounding, susceptibility to sycophancy, and treatment of the self as a singular entity. This study integrates Internal Family Systems (IFS) theory with multi-agent AI technology, externalizing internal parts — Managers, Firefighters, and Exiles — as distinct agents in a fully automated conversational system for mild everyday anxiety. Ten participants completed an IFS pre-assessment, a multi-agent dialogue session, and a post-session interview. Qualitative findings suggest that participants experienced the agents' contrasting stances as challenging their habitual thinking, and several described shifting toward a more observational "Self" perspective. Most participants described the automatically generated emotional summaries as cognitive anchors that organized scattered emotional content into structured self-understanding. These exploratory findings suggest IFS-grounded multi-agent design as a promising direction for emotional well-being in HCI, warranting controlled evaluation.
Keywords: Multi-Agent System, Internal Family Systems, Self-Dialogue, Conversational AI, Human-Computer Interaction
DOI: 10.54941/ahfe1008373
Cite this paper
More from this volume
- AI-Enhanced Live-Streamed English Language Learning: Designing and Evaluating an Intelligent Platform for Chinese Learners
- "They Will Move": Confirmation Bias, Expectation Frames, and Premature Monitoring Drop Off in COLREG Encounters
- Automation transparency communication does not improve supervisory control performance, but shapes operator trust
- The influence of neuroticism on startle and surprise response: a flight simulator study
- EEG-Based Classification of Reward, Penalty, and Movement Events Across Four Video Games of Varying Complexity
- The Effects of Task Similarity and Time Pressure on Task Performance Following Interruptions in Complex Human-Computer Interaction Systems
- Trusting the Chain, Not the Black Box: A Provenance-Based Architecture for Human-Machine Teaming in Military Autonomy
- Design of a Simplified Humanoid Robot Face: Cultural Differences and Emotional Synchronization
- From Visual Observation to Auditory Interaction: A Human-Centered Tangible Music System Based on Physical Objects
- The Impact of Scarcity-Based Dark Patterns on User Performance, Perceived Darkness, and Workload in Subscription Services
- A Behavioral Observation Tool for Diagnosing Human–AI Interaction Profiles in Engineering Design Education
- The Mediated Moon: Semantic Mediation Between Gesture and Generative Image


AHFE Open Access