CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI Counseling

2025-09-29

AI Summary

Existing AI-based psychotherapy research predominantly employs one-shot generation for multi-turn dialogue synthesis, resulting in low therapeutic fidelity and opaque clinical decision-making logic. Method: This paper proposes a memory-driven progressive dialogue synthesis framework that integrates structured outline extraction, memory augmentation, global planning, and strategy reasoning. It introduces, for the first time, Markov Decision Processes (MDPs) into multi-agent collaborative optimization to enable dynamic co-evolution of therapeutic goals, resource allocation, and intervention strategies. Each response incorporates an explicit chain-of-reasoning to ensure clinical plausibility and logical coherence. Contribution/Results: Human evaluation demonstrates statistically significant improvements over state-of-the-art synthetic paradigms in both therapeutic fidelity and interpretability, validating the framework’s capacity to generate clinically grounded, transparent, and adaptive therapeutic dialogues.

Technology Category

• Multiagent Systems: Adversarial Agents
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• Improving therapy fidelity in AI counseling dialogues
• Capturing decision-making rationale behind counseling responses
• Enhancing logical coherence through structured dialogue synthesis

Innovation

• Progressive Dialogue Synthesis strategy for therapy fidelity
• Memory-Driven Dynamic Planning for decision-making rationale
• Multi-agent optimizer attaches chain-of-thought to dialogues