AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling
🤖 AI Summary
Current CBT chatbots suffer from rigid architectures, limited self-optimization capabilities, and low response relevance, hindering clinical applicability. To address these limitations, we propose a multi-agent CBT framework driven by dynamic routing and supervisory feedback mechanisms, emulating real-world therapeutic workflows to enable autonomous iterative refinement and high-quality single-turn response generation. The framework integrates Quora/YiXinLi single-turn dialogue data, a bilingual evaluation benchmark, learnable dynamic routing policies, and a supervision-driven feedback loop, built upon large language models to yield a scalable and empirically verifiable CBT agent system. Experimental results demonstrate significant improvements in response relevance, clinical plausibility, and intervention appropriateness across bilingual single-turn counseling tasks, validating both the framework’s efficacy and its cross-lingual generalization capability.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
Automated Chatbots
Cognitive Behavioral Therapy
Self-Optimization
Innovation
Methods, ideas, or system contributions that make the work stand out.
AutoCBT
cognitive behavioral therapy
self-optimizing robotic system
🔎 Similar Papers
No similar papers found.
