GlucoAgent: Personalized Glucose Forecasting from Multimodal Personal Context
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Journal ref: GenAI for Health Workshop @ NeurIPS 2026, Sydney
Code: https://github.com/JHU-CDHAI/cgmlsm
License: http://creativecommons.org/licenses/by/4.0/
The gist: Continuous glucose monitors, smartwatches, meal logs, and health profiles form a rich multimodal personal context that can significantly enhance glucose forecasting.
Abstract
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.
Sources
- Chronos: Learning the Language of Time Series
- Chronos-2: From Univariate to Universal Forecasting
- DM-Bench: Benchmarking LLMs for Personalized Decision Making in Diabetes Management
- A decoder-only foundation model for time-series forecasting
- Retrieval Augmented Time Series Forecasting
- The Anatomy of a Personal Health Agent
- SSM-CGM: Interpretable State-Space Forecasting Model of Continuous Glucose Monitoring for Personalized Diabetes Management
- MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes
- GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
- Moirai 2.0: When Less Is More for Time Series Forecasting
- Timer: Generative Pre-trained Transformers Are Large Time Series Models
- GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting
- CastFlow: Bridging Evidence Acquisition and Accurate Prediction in Agentic Time Series Forecasting
- Can LLM Coding Agents Reason About Time Series?
- PULSE: Agentic Investigation with Passive Sensing for Proactive Affective Intervention in Cancer Survivorship
- Context is Key: A Benchmark for Forecasting with Essential Textual Information
- Unified Training of Universal Time Series Forecasting Transformers
- TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents