Saved in:
Bibliographic Details
Main Authors: Wang, Fei, Yang, Jiangnan, Chen, Junjie, Liu, Yuxin, Li, Kun, Wei, Yanyan, Guo, Dan, Wang, Meng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.06583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914376084094976
author Wang, Fei
Yang, Jiangnan
Chen, Junjie
Liu, Yuxin
Li, Kun
Wei, Yanyan
Guo, Dan
Wang, Meng
author_facet Wang, Fei
Yang, Jiangnan
Chen, Junjie
Liu, Yuxin
Li, Kun
Wei, Yanyan
Guo, Dan
Wang, Meng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06583
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being
Wang, Fei
Yang, Jiangnan
Chen, Junjie
Liu, Yuxin
Li, Kun
Wei, Yanyan
Guo, Dan
Wang, Meng
Human-Computer Interaction
Computers and Society
Machine Learning
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.
title XInsight: Integrative Stage-Consistent Psychological Counseling Support Agents for Digital Well-Being
topic Human-Computer Interaction
Computers and Society
Machine Learning
url https://arxiv.org/abs/2603.06583