A Closed-Loop Multi-Agent System Driven by LLMs for Meal-Level Personalized Nutrition Management
This work addresses the challenge of providing integrated, meal-level dietary support for individuals, though it is incremental as it builds on existing components like LLMs and vision agents.
The paper tackles the problem of fragmented personalized nutrition management by developing a closed-loop multi-agent system driven by LLMs that integrates meal logging, nutrient analysis, and recommendations, achieving competitive nutrient estimation and personalized menus in experiments with SNAPMe images and simulated users.
Personalized nutrition management aims to tailor dietary guidance to an individual's intake and phenotype, but most existing systems handle food logging, nutrient analysis and recommendation separately. We present a next-generation mobile nutrition assistant that combines image based meal logging with an LLM driven multi agent controller to provide meal level closed loop support. The system coordinates vision, dialogue and state management agents to estimate nutrients from photos and update a daily intake budget. It then adapts the next meal plan to user preferences and dietary constraints. Experiments with SNAPMe meal images and simulated users show competitive nutrient estimation, personalized menus and efficient task plans. These findings demonstrate the feasibility of multi agent LLM control for personalized nutrition and reveal open challenges in micronutrient estimation from images and in large scale real world studies.