XInsight用多智能体框架让心理聊天机器人更像真实咨询，分阶段、有依据、可追踪。
XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being
- 按探索-洞察-行动流程设计多智能体协作，每步都有专业角色分工。
- 支持多种疗法动态切换，生成标准化心理记录与预防计划，提升可解释性。
- 适合开发数字健康应用的团队，尤其关注心理咨询系统透明化与有效性的人。
基于网络的心理支持平台日益普及，但多数大模型驱动的聊天机器人仍缺乏透明度、仅单阶段运行且与临床实践脱节，难以支撑数字健康应用。为此，我们提出XInsight——一种受心理咨询启发的多智能体框架，将心理支持建模为符合经典‘探索-洞察-行动’范式的阶段一致工作流。基于结构化用户表征，XInsight通过统一的‘推理-干预-反思’循环协调多个专用智能体：探索代理整理背景信息并生成结构化案情概念化表，路由代理在积极心理治疗（SFBT）、认知行为疗法（CBT）和正念认知疗法（MBCT）间进行自适应治疗路由（ATR），统一干预代理执行阶段一致的子模块，整合代理指导回顾、技能融合与复发预防规划。记录代理持续将开放式对话转化为标准化心理文档，包括案情分析、治疗记录与复发预防计划，增强可解释性、连续性与问责性。为实现严谨透明评估，我们引入XInsight-Bench与尺度引导的LLM评估（SGLE）协议，结合疗法特异性临床量表与通用咨询标准。实验表明，相比现有系统，XInsight在范式契合度、多疗法整合能力、交互深度与可解释性上均有显著提升，为心理支持智能体在数字健康应用中的落地提供了可行蓝图。
原文摘要 · Abstract (English)
Web-based platforms are becoming a primary channel for psychological support, yet most LLM-driven chatbots remain opaque, single-stage, and weakly grounded in established therapeutic practice, limiting their usefulness for web applications that promote digital well-being. To address this gap, we present \textbf{XInsight}, a counseling-inspired multi-agent framework that models psychological support as a stage-consistent workflow aligned with the classical \textit{Exploration-Insight-Action} paradigm. Building on structured client representations, XInsight orchestrates specialized agents under a unified \textit{Reason-Intervene-Reflect} cycle: an Exploration agent organizes background and concerns into a structured Case Conceptualization Form, a Routing agent performs Adaptive Therapeutic Routing (ATR) across SFBT, CBT, and MBCT, a unified Therapeutic agent executes school-consistent submodules, and a Consolidation agent guides review, skill integration, and relapse-prevention planning. A Recording agent continuously transforms open-ended web dialogues into standardized psychological artifacts, including case formulations, therapeutic records, and relapse-prevention plans, enhancing interpretability, continuity, and accountability. To support rigorous and transparent assessment, we introduce \textbf{XInsight-Bench} with a Scale-Guided LLM Evaluation (SGLE) protocol that combines therapy-specific clinical scales with general counseling criteria. Experiments show improved paradigm alignment, multi-therapy integration, interaction depth, and interpretability over existing multi-agent counseling systems, indicating that XInsight provides a practical blueprint for integrating counseling-inspired support agents into web applications for digital well-being.
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。