Year: 2026
Type: conference-paper
Abstract: Longitudinal healthcare agents require persistent state tracking under temporal uncertainty.In domains like chronic disease management, patient states-medications, symptoms, and vital signs-evolve continuously over months.Existing memory architectures for Large Language Models (LLMs) are inherently retrieval-centric: they treat memory as a static repository of past interactions, failing to resolve conflicting or superseded information when queried for the current patient state.We propose a shift to state-centric memory.Our framework introduces (1) a bi-temporal state representation that decouples event time from ingestion time and tracks temporal validity windows, (2) an incremental state arbitration mechanism using four operators-SUPPORT, REFINE, SU-PERSEDE, and BRANCH-CONFLICT-to handle evolving medical facts without destructive overwriting, and (3) a confidence-thresholded evidence escalation layer for robust, efficient memory access.Evaluated on a longitudinal diabetes management suite as a representative biomedical state tracking task, our method achieves a Unique-F1 of 0.85 and Conflict-F1 of 0.98, substantially improves upon longcontext LLMs (0.38 / 0.89) and standard vector memory (0.30 / 0.60), demonstrating that agentic AI in longitudinal biomedical settings requires continuous, evidence-grounded arbitration rather than simple retrieval.
Authors: Jianing Zhao, Xiaoquan Zhi, Xinqiang Yu
Institution: Tianjin University
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W7166862900