AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling

TL;DR

AutoCBT introduces an autonomous multi-agent framework leveraging LLMs for improved automated cognitive behavioral therapy, demonstrating higher-quality responses in psychological counseling scenarios.

Contribution

This work presents a novel multi-agent framework for automated CBT that enhances response quality and self-optimization compared to existing fixed-structure systems.

Findings

AutoCBT achieves higher response quality in single-turn consultations.

The framework demonstrates effective self-optimization and adaptability.

Experimental results validate its applicability in psychological counseling.

Abstract

Traditional in-person psychological counseling remains primarily niche, often chosen by individuals with psychological issues, while online automated counseling offers a potential solution for those hesitant to seek help due to feelings of shame. Cognitive Behavioral Therapy (CBT) is an essential and widely used approach in psychological counseling. The advent of large language models (LLMs) and agent technology enables automatic CBT diagnosis and treatment. However, current LLM-based CBT systems use agents with a fixed structure, limiting their self-optimization capabilities, or providing hollow, unhelpful suggestions due to redundant response patterns. In this work, we utilize Quora-like and YiXinLi single-round consultation models to build a general agent framework that generates high-quality responses for single-turn psychological consultation scenarios. We use a bilingual dataset to evaluate the quality of single-response consultations generated by each framework. Then, we incorporate dynamic routing and supervisory mechanisms inspired by real psychological counseling to construct a CBT-oriented autonomous multi-agent framework, demonstrating its general applicability. Experimental results indicate that AutoCBT can provide higher-quality automated psychological counseling services.