A Closed-Loop Multi-Agent System Driven by LLMs for Meal-Level Personalized Nutrition Management

TL;DR

This paper introduces a novel multi-agent system driven by large language models that provides personalized, meal-level nutrition management by integrating image-based food logging, nutrient estimation, and adaptive meal planning.

Contribution

It presents a new closed-loop mobile nutrition assistant combining vision, dialogue, and state management agents for personalized dietary guidance.

Findings

Achieves competitive nutrient estimation from meal images

Provides personalized meal plans based on user preferences

Demonstrates effective multi-agent LLM control in nutrition management

Abstract

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.