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

2026-01-25

AI Summary

This work addresses a critical limitation in existing mental health question-answering systems, which predominantly rely on the “top-down” rational restructuring of cognitive behavioral therapy while neglecting embodied experience and core emotional processing. To bridge this gap, we propose the first emotion-focused therapy (EFT)-based multi-agent chain-of-thought framework, implementing a three-stage pipeline—embodied sensing, cognitive exploration, and narrative intervention—to deliver highly empathetic and interpretable psychological support. Our key contributions include the construction of a high-quality EFT-Instruct dataset, the design of a multi-agent collaboration mechanism, and the integration of chain-of-thought distillation, embodied perception mapping, and narrative reconstruction techniques. Experimental results demonstrate that our model, EFT-LLM, significantly outperforms strong baselines and human responses in both empathy depth and clinical fidelity, with ablation studies confirming the efficacy of the multi-agent architecture.

Technology Category

• Humans and AI: Emotional Intelligence
• Intelligent Robots: Embodied AI
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• 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
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Emotion-Focused Therapy
• Mental Health Question Answering
• Large Language Models
• Embodied Experience
• Primary Emotion Processing

Innovation

• Emotion-Focused Therapy
• Multi-Agent Chain-of-Thought
• Embodied Perception
• EFT-LLM
• Mental Health Question Answering