EFT-CoT: A Multi-Agent Chain-of-Thought Framework for Emotion-Focused Therapy

Abstract

Leveraging Large Language Models (LLMs) for Mental Health Question Answering (MHQA) is promising for mitigating resource shortages. However, existing Cognitive Behavioral Therapy (CBT)-based approaches predominantly favor a "top-down" rational restructuring, often neglecting clients' embodied experiences and primary emotion processing. To address this, we propose an Emotion-Focused Therapy (EFT)-based Multi-Agent Chain-of-Thought framework (EFT-CoT). Adopting a "bottom-up" trajectory, it deconstructs the intervention into a three-stage reasoning flow: "Embodied Perception - Cognitive Exploration - Narrative Intervention." Utilizing eight specialized agents, the system explicitly executes critical components such as somatic awareness mapping, adaptive assessment, core belief extraction, and narrative restructuring. We further constructed "EFT-Instruct," a high-quality dataset via Chain-of-Thought distillation of approximately 67,000 authentic texts, and fine-tuned a specialized model, EFT-LLM. Experimental evaluations demonstrate that EFT-LLM outperforms strong baselines and human responses across metrics like empathy depth and structural professionalism. Ablation studies confirm the necessity of the multi-agent mechanism. The model exhibits superior psychological reasoning, offering an effective pathway for interpretable, high-empathy counseling systems.