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.

翻译：利用大型语言模型进行心理健康问答有望缓解资源短缺问题。然而，现有的基于认知行为疗法的方法主要偏向于"自上而下"的理性重构，常常忽视来访者的具身体验和初级情绪处理。为解决这一问题，我们提出了一种基于情绪聚焦疗法的多智能体思维链框架。该框架采用"自下而上"的路径，将干预解构为三阶段推理流程："具身感知 - 认知探索 - 叙事干预"。系统利用八个专门设计的智能体，明确执行诸如躯体意识映射、适应性评估、核心信念提取和叙事重构等关键组件。我们进一步通过思维链蒸馏约67,000条真实文本，构建了高质量数据集"EFT-Instruct"，并微调了一个专用模型EFT-LLM。实验评估表明，EFT-LLM在共情深度和结构专业性等指标上均优于强基线模型和人工回复。消融研究证实了多智能体机制的必要性。该模型展现出卓越的心理推理能力，为构建可解释、高共情度的咨询系统提供了有效路径。