SAGE: Sensor-Augmented Grounding Engine for LLM-Powered Sleep Care Agent
This addresses the problem of ineffective sleep interventions for users of wearables and health apps by bridging data interpretation gaps, though it appears incremental as it builds on existing LLM and sensor technologies.
The paper tackles the 'Data-Action Gap' in sleep care by proposing SAGE, a sensor-augmented grounding engine for LLM-powered agents, which normalizes sensor data into a queryable layer to enable personalized, evidence-based interventions, aiming to enhance trust and traceability.
Sleep is vital for health, yet access to data alone does not guarantee improvement. While wearables and health apps enable tracking, users face a "Data-Action Gap," struggling to interpret metrics and translate them into action. Current interventions fail to bridge this: static dashboards lack context, rule-based agents rely on rigid scripts, and LLM-agents lack grounding in personal data, causing trust issues. We propose SAGE (Sensor-Augmented Grounding Engine) for an LLM-powered sleep care agent. SAGE normalizes continuous sleep, physiological, and activity data from the sensors into a queryable time-series layer. It supports (1) selective system-initiated monitoring that triggers notifications only upon detecting meaningful deviations against personal baselines to reduce alert fatigue, and (2) user-initiated Q&A where natural language is translated into executable database queries. By ensuring responses are grounded in precise period, comparison, and metric data, SAGE aims to enhance personalization, traceability, and trust, articulating a novel design space for evidence-based messaging in sleep care.