GlucoAgent: Personalized Glucose Forecasting from Multimodal Personal Context (Meta Reality Labs; arXiv 2611.04126)

Agent: Claude Opus 5 at high reasoning effort, fixed before test scoring. Tools: retrieval of similar past meals, physiological and statistical model fitting, back-testing. Benchmarks: CGMacros (multimodal), GlucoFM-Bench (9 glucose-only datasets), OhioT1DM under the CGM-LSM protocol.

• Form factor: wrist + CGM

Continuous glucose monitors, smartwatches, meal logs, and health profiles form a rich multimodal personal context that can significantly enhance glucose forecasting. However, existing methods struggle to effectively utilize these signals to improve glucose prediction because the relevance of different modalities varies drastically across individuals and time. We present GlucoAgent, an LLM-based agentic system that addresses this challenge through dynamic, case-by-case analysis at inference time. For each forecast, GlucoAgent writes and runs code over an individual's multimodal context and returns predictions with a reason and supporting evidence. The generated programs are highly diverse, ranging from retrieving similar past meals to fitting and back-testing physiological and statistical models. On CGMacros, a multimodal glucose dataset, GlucoAgent outperforms time series foundation models on every forecasting horizon, achieving an average RMSE of 22.5 mg/dL compared to 23.5 mg/dL of Chronos-2, the leading multimodal time series foundation model. Furthermore, GlucoAgent is highly effective at leveraging multimodal data. The addition of multimodal data reduces its average RMSE by 1.4 mg/dL (24.0 mg/dL to 22.5 mg/dL), compared to a marginal 0.3 mg/dL (23.8 mg/dL to 23.5 mg/dL) improvement for Chronos-2. This advantage is most pronounced in challenging post-meal windows, where GlucoAgent uses multimodal context to reduce 60-minute forecast RMSE by 4.6 mg/dL (31.0 mg/dL to 26.5 mg/dL), far exceeding the 0.8 mg/dL (31.9 mg/dL to 31.1 mg/dL) reduction achieved by Chronos-2.

Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

• CGMacros: dual-CGM + Fitbit + meal macronutrients/photos in healthy, pre-diabetes and T2D adults (PhysioNet)Evaluation45 subjects · Glucose · Activity

• GlucoAgentllmcode-writing LLM agent for personalised glucose forecasting from CGM + smartwatch + mealsGlucoseHRmeal logs/photos2026