CGM-Agent uses LLMs solely as reasoning engines to select local analytical functions for private question answering over continuous glucose data, achieving 94% accuracy on synthetic queries and 88% on real-world ones in a new 4180-question benchmark.
Analyze glucose excursions for {dates_str}. Find significant rapid changes and details on timing, magnitude, and speed
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
If Only My CGM Could Speak: A Privacy-Preserving Agent for Question Answering over Continuous Glucose Data
CGM-Agent uses LLMs solely as reasoning engines to select local analytical functions for private question answering over continuous glucose data, achieving 94% accuracy on synthetic queries and 88% on real-world ones in a new 4180-question benchmark.