AI PsyRoom: Artificial Intelligence Platform for Segmented Yearning and Reactive Outcome Optimization Method

2025-06-07

AI Summary

To address the scarcity of psychological counseling resources and the limitations of existing large language models—namely, coarse-grained emotion understanding and insufficient capability for personalized intervention—this paper proposes EmoPsy, a multi-agent psychological counseling framework. We introduce a novel fine-grained emotion taxonomy comprising 35 emotion categories and design a dual-agent collaborative architecture: PsyRoom A reconstructs high-fidelity therapeutic dialogues, while PsyRoom B generates individualized treatment plans. Integrating multi-agent simulation, fine-grained emotion recognition, and treatment plan generation, we construct the open-source EmoPsy dialogue dataset (12,350 turns across 423 clinical scenarios). Experiments demonstrate statistically significant improvements—18%, 23%, 24%, and 16%—in problem orientation, expressive capacity, empathic responsiveness, and interaction quality, respectively. Both the EmoPsy model and dataset are publicly released under an open-source license.

Technology Category

• Humans and AI: Emotional Intelligence
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Psychological counseling faces huge challenges due to the growing demand for mental health services and the shortage of trained professionals. Large language models (LLMs) have shown potential to assist psychological counseling, especially in empathy and emotional support. However, existing models lack a deep understanding of emotions and are unable to generate personalized treatment plans based on fine-grained emotions. To address these shortcomings, we present AI PsyRoom, a multi-agent simulation framework designed to enhance psychological counseling by generating empathetic and emotionally nuanced conversations. By leveraging fine-grained emotion classification and a multi-agent framework, we construct a multi-agent PsyRoom A for dialogue reconstruction, generating a high-quality dialogue dataset EmoPsy, which contains 35 sub-emotions, 423 specific emotion scenarios, and 12,350 dialogues. We also propose PsyRoom B for generating personalized treatment plans. Quantitative evaluations demonstrate that AI PsyRoom significantly outperforms state-of-the-art methods, achieving 18% improvement in problem orientation, 23% in expression, 24% in Empathy, and 16% in interactive communication quality. The datasets and models are publicly available, providing a foundation for advancing AI-assisted psychological counseling research.

Problem

• Addresses shortage of mental health professionals with AI assistance
• Improves emotion understanding and personalized treatment plans in counseling
• Enhances counseling quality via multi-agent empathetic dialogue generation

Innovation

• Multi-agent framework for nuanced counseling
• Fine-grained emotion classification system
• Generates personalized treatment plans