Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| 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 |