BALMS is a benchmark for evaluating large language model (LLM) agents that analyze longitudinal wearable data to predict mental‑health wellbeing scores and generate evidence‑grounded rationales. It covers three real‑world datasets, two task families (score prediction and rationale generation), and tests five LLM backbones across open‑ and closed‑source paradigms. The study finds that zero‑shot agents rarely beat a simple mean baseline, and while chain‑of‑thought prompting helps reasoning, it does not ensure temporal grounding or numerical accuracy.
By Yu Yvonne Wu, Arvind Pillai, Yuliang Chen, Yuwei Zhang, Sudarshan Regmi, Tess Z. Griffin, Michael V. Heinz, Lisa A. Marsch, Nicholas C. Jacobson, Andrew Campbell
arXiv:2606. 00345v1 Announce Type: new Abstract: Wearable and mobile sensing technologies enable continuous monitoring of human behavior and health in real-world settings.
By Flavio Di Martino, Mattia G. Campana, Marcello Magno, Lorenza Pratali, Franca Delmastro
arXiv:2607. 25679v1 Announce Type: cross Abstract: Multimodal behavioral analysis offers a scalable approach to assessing depression, anxiety, and stress, yet generic fusion models often ignore the psychometric structure of questionnaire labels.
By Shiyu Teng, Haichen Yu, Jiaqing Liu, Hao Sun, Yu Song, Shurong Chai, Ruibo Hou, Lanfen Lin, Yen-Wei Chen
arXiv:2608. 07518v1 Announce Type: cross Abstract: Longitudinal, in-the-wild, wearable sensing yields day-level physiology, sleep, activity, and environmental streams, whereas affect and cognition are labeled only episodically (per waves).
By Igor Matias, Maximilian Haas, Eric J. Daza, Matthias Kliegel, Katarzyna Wac
The study investigates how a large language model, Gemma-3-27B-PT, internally represents depressive symptoms. By applying mechanistic interpretability methods to the model’s residual stream, researchers found that symptom groups are geometrically distinct at layer 21, and that projected symptom vectors align with clinician-annotated rankings across mood, somatic, and suicidality dimensions. Additionally, a single depression vector at this layer can differentiate depressive from non-depressive text with an AUC of 0.789, suggesting a potential emotional valence gate for symptom projection.
By Fangyi Zhu, Ajay Subramanian, Allison Constant, Camille Wang, Ravish Gupta, Corey J. Keller
arXiv:2608. 13316v1 Announce Type: cross Abstract: Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence of their advantages is lacking.
By Alexander Br\"auer, Benjamin Cauchi, Nils Strodthoff