智能体
arxiv.org ·
MACBT：具有纵向记忆的多智能体认知行为治疗决策支持系统
该 arXiv 预印本提出面向临床医生的 AI 决策支持系统 MACBT，将 CBT 五阶段工作流（评估、苏格拉底式提问、认知重构、行为实验、治疗监测）编码为五个协作 agent，并配套 CBT 专用纵向记忆模块 CD Memory，跨会话追踪认知扭曲类型、频率、严重度与重构效果，生成会前病理报告和干预优先级建议。作者通过双角色大模型模拟构建中文 CBT 对话语料，对 Qwen3-14B 进行监督微调与直接偏好优化。GPT-4 评判显示 MACBT 在专业性和临床真实性上优于 MeChat、SoulChat、PsyChat、CPsyCounX，完整记忆增强系统使会话质量提升 12.6%，跨会话连续性、干预进展与个性化均值达 2.29。
AI推荐理由 arXiv 预印本，作者与摘要信息完整，方法描述具体（五阶段 CBT 工作流映射为五个协作 agent，CD Memory 跨会话追踪认知扭曲类型/频率/严重度/重构效果，基于 Qwen3-14B 做 SFT+DPO，用 GPT-4 作为评判）。新信息在于将多智能体与纵向记忆结合用于 CBT 临床决策支持，并给出相对 MeChat、SoulChat、PsyChat、CPsyCounX 的专业性（2.62）与临床真实性（2.25）对比，以及记忆增强后会话质量提升 12.6%、跨会话连续性均值 2.29。局限：语料由双角色 LLM 模拟生成而非真实临床数据，评估依赖 GPT-4 评判，未提供真实临床验证或部署效果，属预印本未经同行评审。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.30939 (cs)
[Submitted on 25 Sep 2026]
Title:MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory
Authors:De Jiang, Shuo Zhang, Weiwei Liao, Jianying Zhang, Chuanhui Yu, Hongen Liao, Kehong Yuan
View a PDF of the paper titled MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory, by De Jiang and 6 other authors
View PDF
HTML (experimental)
Abstract:Cognitive behavioral therapy (CBT) is an evidence-based first-line treatment for depression, yet its scale is constrained by the time clinicians spend on pre-session preparation, post-session documentation, and longitudinal cognitive-pathology tracking. We present a clinician-facing AI decision-support system that combines a multi-agent CBT framework (MACBT) with a CBT-specific longitudinal memory module (CD Memory). MACBT encodes the five-stage CBT workflow (assessment, Socratic questioning, cognitive restructuring, behavioral experiments, and treatment monitoring) into five collaborative agents. CD Memory tracks cognitive-distortion type, frequency, severity, and restructuring efficacy across sessions to generate pre-session pathology reports and intervention-priority recommendations. We construct a Chinese CBT dialogue corpus via dual-role large language model simulation and train a Qwen3-14B backbone with supervised fine-tuning and direct preference optimization. Evaluation with GPT-4 judges shows MACBT outperforms MeChat, SoulChat, PsyChat, and CPsyCounX in professionalism (2.62) and clinical authenticity (2.25). The full memory-augmented system further improves session quality by 12.6% and achieves a longitudinal mean of 2.29 on cross-session continuity, intervention progression, and personalization.
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.30939 [cs.AI]
(or
arXiv:2609.30939v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.30939
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: De Jiang [view email]
[v1]
Fri, 25 Sep 2026 07:54:45 UTC (5,837 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled MACBT: A Multi-Agent Cognitive Behavioral Therapy Decision Support System with Longitudinal Memory, by De Jiang and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)