cs.MANov 17, 2026

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

Authors: Yishu Ji, Zhihan Jiang, Will Ke Wang, Yuang Fan, Anind K. Dey, Xuhai "Orson" Xu

Organizations: Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, United States · Biomedical Informatics, Columbia University, New York, New York, United States · Columbia University, New York, New York, United States · Information School, University of Washington, Seattle, Washington, United States

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 OAK-Mind, a zerO-training, multi-Agent, Knowledge-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.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health Sensing

    Aug 27, 2026Yu Yvonne Wu, Arvind Pillai, Yuliang Chen +7AI Agent BenchmarksMental Health

  2. TimeSRL: Generalizable Time-Series Behavioral Modeling via Semantic RL-Tuned LLMs -- A Case Study in Mental Health

    May 20, 2026Yuang Fan, Lilin Xu, Millie Wu +8Mental HealthDomain Generalization

  3. OMIND: Framework for Knowledge Grounded Finetuning and Multi-Turn Dialogue Benchmark for Mental Health LLMs

    Mar 26, 2026Suraj Racha, Prashant Harish Joshi, Utkarsh Maurya +6Medical LLMsLLM Fine-Tuning