{"ID":2862482,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25733","arxiv_id":"2509.25733","title":"CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI Counseling","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.","short_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....","url_abs":"https://arxiv.org/abs/2509.25733","url_pdf":"https://arxiv.org/pdf/2509.25733v1","authors":"[\"Mingyu Chen\",\"Jingkai Lin\",\"Zhaojie Chu\",\"Xiaofen Xing\",\"Yirong Chen\",\"Xiangmin Xu\"]","published":"2025-09-30T03:44:00Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}