跳到正文
arXiv cs.AI· Yishu Ji, Zhihan Jiang, Will Ke Wang, Yuang Fan, Anind K. Dey, Xuhai "Orson" Xu·· 2 小时前AI 评分39

OAK-Mind:基于知识驱动的多智能体 LLM,从被动传感数据零训练推断心理健康变化

OAK-Mind: Zero-Training Mental Health Change Inference from Passive Sensing via Knowledge-Grounded Multi-Agent LLMs

AI 导读

研究者提出 OAK-Mind,一个零训练的多智能体、知识驱动 LLM 管线,从可穿戴与手机传感数据推断心理健康变化。该管线将传感数据组织为睡眠、体力活动、位置移动和手机使用等行为维度,由多个基于心理健康文献的专用智能体解读纵向行为变化,并结合问卷症状评分给出可读的推断依据。在多个数据集和任务上,无需任务特定训练的 OAK-Mind 达到或超过监督基线性能,并在四个 LLM 骨干上均优于直接提示。

正文 · 原文

View PDF HTML (experimental)

Abstract:Wearable and smartphone sensors capture behavioral signals associated with mental health, yet inferring mental health outcomes from these signals has traditionally relied on supervised models requiring labeled data and offering limited insight into their predictions. Large language models (LLMs) offer new opportunities to reason over behavioral evidence, but existing LLM-based approaches to passive sensing have largely continued to rely on task-specific fine-tuning or sensor-specific pretraining. In this paper, we introduce \textbf{OAK-Mind}, a zer\textbf{O}-training, multi-\textbf{A}gent, \textbf{K}nowledge-grounded LLM pipeline for inferring mental health changes from passive sensing data. The pipeline organizes sensing data into behavioral dimensions including sleep, physical activity, location mobility, and smartphone use, and orchestrates specialized agents grounded in mental health literature to interpret longitudinal behavioral changes. It synthesizes their assessments and applies questionnaire-based symptom rating to infer changes relative to an individual's baseline assessment with human-readable rationale grounded in observed behavioral patterns and domain knowledge. Across datasets and prediction tasks, while without task-specific training, OAK-Mind achieves comparable or better performance than the most predictive supervised baselines trained on additional labeled samples. It also demonstrate consistent improvement upon direct prompting across four tested LLM backbones. Ablation analyses support the benefits of combining behavioral interpretation with symptom rating, distributing analysis across domain-specific agents, and incorporating domain knowledge. Our findings highlight the potential of knowledge-grounded, multi-agent LLMs for training-free inference of mental health changes from passive sensing data.
Comments: Under review at ACM IMWUT. 30 pages, 4 figures and 6 tables
Subjects: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
Cite as: arXiv:2611.22248 [cs.MA]
  (or arXiv:2611.22248v1 [cs.MA] for this version)
  https://doi.org/10.48550/arXiv.2611.22248

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yishu Ji [view email]
[v1] Tue, 17 Nov 2026 05:52:52 UTC (2,591 KB)

来源:arXiv cs.AI · arxiv.org