MIND: Towards Immersive Psychological Healing with Multi-agent Inner Dialogue

TL;DR

The paper introduces MIND, a multi-agent inner dialogue framework using large language models to create immersive, emotionally adaptive psychological healing environments, outperforming traditional methods in user experience.

Contribution

MIND is a novel multi-agent paradigm that leverages LLMs for role-based inner dialogues, enhancing emotional depth and immersion in psychological healing.

Findings

MIND provides a more user-friendly experience than traditional paradigms.

Human experiments show MIND's effectiveness in real-world healing scenarios.

MIND leverages LLMs' generative and role-playing abilities for emotional engagement.

Abstract

Mental health issues are worsening in today's competitive society, such as depression and anxiety. Traditional healings like counseling and chatbots fail to engage effectively, they often provide generic responses lacking emotional depth. Although large language models (LLMs) have the potential to create more human-like interactions, they still struggle to capture subtle emotions. This requires LLMs to be equipped with human-like adaptability and warmth. To fill this gap, we propose the MIND (Multi-agent INner Dialogue), a novel paradigm that provides more immersive psychological healing environments. Considering the strong generative and role-playing ability of LLM agents, we predefine an interactive healing framework and assign LLM agents different roles within the framework to engage in interactive inner dialogues with users, thereby providing an immersive healing experience. We conduct extensive human experiments in various real-world healing dimensions, and find that MIND provides a more user-friendly experience than traditional paradigms. This demonstrates that MIND effectively leverages the significant potential of LLMs in psychological healing.