Reproduce “GlucoAgent: Personalized Glucose Forecasting from Multimodal Personal Context” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xingzhi Sun, Hyo Jin Kim, Zhiyuan Wang, Hao Chen
GlucoAgent selects analyses for glucose forecasts: an LLM inspects personal history, writes and runs Python, then submits predictions with evidence. In tests of nine participants, multimodal inputs had mean RMSE 22.5 mg/dL across four horizons, versus 23.5 for Chronos-2; post-meal 60-minute RMSE fell 4.6 mg/dL. This pilot result is limited to one dataset and does not establish clinical benefit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.