CATCH通过分阶段生成与记忆驱动规划，提升AI心理咨询对话的真实性和逻辑性。
CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI Counseling
- 分阶段生成对话，基于用户自述结构化提炼目标与方案
- 引入记忆增强的动态规划机制，使每轮回复有明确推理链条
- 多智能体优化器结合马尔可夫决策过程，生成可解释的思考路径
近期基于大语言模型的AI心理咨询取得显著进展。但现有研究采用一次性生成方式合成多轮对话，导致治疗真实度低，且无法捕捉每条回复背后的决策逻辑。本文提出CATCH，一种新型数据合成框架，以解决上述问题。为提升治疗真实性，引入渐进式对话生成策略：从用户自述中提取目标、资源与解决方案，形成结构化提纲，再逐阶段生成对齐咨询阶段的对话。为捕捉回应背后的决策理由，提出记忆驱动的动态规划思维模式，融合记忆增强、全局规划与策略推理；协同多智能体优化器利用马尔可夫决策过程，为每轮对话附加显式的思维链。大量实验与人工评估表明，CATCH显著提升了AI心理咨询的治疗真实度与逻辑连贯性。
原文摘要 · Abstract (English)
Recently, advancements in AI counseling based on large language models have shown significant progress. However, existing studies employ a one-time generation approach to synthesize multi-turn dialogue samples, resulting in low therapy fidelity and failing to capture the decision-making rationale behind each response. In this work, we propose CATCH, a novel data synthesis framework designed to address these challenges. Specifically, to improve therapy fidelity, we introduce the Progressive Dialogue Synthesis strategy, which extracts goals, resources, and solutions from a client's self-report, organizes them into structured outlines, and then incrementally generates stage-aligned counseling dialogues. To capture decision-making rationale behind each response, we propose the Memory-Driven Dynamic Planning thinking pattern that integrates memory enhancement, global planning, and strategy reasoning; a collaborative multi-agent optimizer then leverages MDP to attach explicit chain-of-thought to each dialogue turn. Extensive experiments and human evaluations demonstrate that CATCH significantly enhances fidelity and logical coherence in AI counseling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。