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

• URL: http://arxiv.org/abs/2601.04491v1
• Date: Thu, 08 Jan 2026 01:51:37 GMT
• Title: A Closed-Loop Multi-Agent System Driven by LLMs for Meal-Level Personalized Nutrition Management
• Authors: Muqing Xu,
• Abstract summary: 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.<n>The system coordinates vision, dialogue and state management agents to estimate nutrients from photos and update a daily intake budget.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• SnappyMeal: Design and Longitudinal Evaluation of a Multimodal AI Food Logging Application [7.101331257479778]
  Food logging plays a critical role in uncovering correlations between diet, medical, fitness, and health outcomes.<n>Current methods, such as handwritten and app-based journaling, are inflexible and result in low adherence and potentially inaccurate nutritional summaries.<n>We propose SnappyMeal, an AI-powered dietary tracking system that leverages multimodal inputs to enable users to more flexibly log their food intake.
  arXiv  Detail & Related papers  (2025-11-05T23:14:22Z)
• NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence [6.937243101289335]
  NutriGen is a framework designed to generate personalized meal plans that align with user-defined dietary preferences and constraints.<n>Our evaluation shows that Llama 3.1 8B and GPT-3.5 Turbo achieve the lowest percentage errors of 1.55% and 3.68%, respectively.
  arXiv  Detail & Related papers  (2025-02-28T00:05:49Z)
• DietGlance: Dietary Monitoring and Personalized Analysis at a Glance with Knowledge-Empowered AI Assistant [36.806619917276414]
  We present DietGlance, a system that automatically monitors dietary in daily routines and delivers personalized analysis from knowledge sources.<n>DietGlance first detects ingestive episodes from multimodal inputs using eyeglasses, capturing privacy-preserving meal images of various dishes being consumed.<n>Based on the inferred food items and consumed quantities from these images, DietGlance further provides nutritional analysis and personalized dietary suggestions.
  arXiv  Detail & Related papers  (2025-02-03T12:46:37Z)
• RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models [96.43285670458803]
  Uni-Food is a unified food dataset that comprises over 100,000 images with various food labels.<n>Uni-Food is designed to provide a more holistic approach to food data analysis.<n>We introduce a novel Linear Rectification Mixture of Diverse Experts (RoDE) approach to address the inherent challenges of food-related multitasking.
  arXiv  Detail & Related papers  (2024-07-17T16:49:34Z)
• NutritionVerse-Direct: Exploring Deep Neural Networks for Multitask Nutrition Prediction from Food Images [63.314702537010355]
  Self-reporting methods are often inaccurate and suffer from substantial bias. Recent work has explored using computer vision prediction systems to predict nutritional information from food images. This paper aims to enhance the efficacy of dietary intake estimation by leveraging various neural network architectures.
  arXiv  Detail & Related papers  (2024-05-13T14:56:55Z)
• How Much You Ate? Food Portion Estimation on Spoons [63.611551981684244]
  Current image-based food portion estimation algorithms assume that users take images of their meals one or two times. We introduce an innovative solution that utilizes stationary user-facing cameras to track food items on utensils. The system is reliable for estimation of nutritional content of liquid-solid heterogeneous mixtures such as soups and stews.
  arXiv  Detail & Related papers  (2024-05-12T00:16:02Z)
• ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework [2.3221599497640915]
  ChatDiet is a novel framework designed specifically for personalized nutrition-oriented food recommendation chatbots. ChatDiet integrates personal and population models, complemented by an orchestrator, to seamlessly retrieve and process pertinent information. Our evaluation of ChatDiet includes a compelling case study, where we establish a causal personal model to estimate individual nutrition effects.
  arXiv  Detail & Related papers  (2024-02-18T06:07:17Z)
• FoodLMM: A Versatile Food Assistant using Large Multi-modal Model [96.76271649854542]
  Large Multi-modal Models (LMMs) have made impressive progress in many vision-language tasks. This paper proposes FoodLMM, a versatile food assistant based on LMMs with various capabilities. We introduce a series of novel task-specific tokens and heads, enabling the model to predict food nutritional values and multiple segmentation masks.
  arXiv  Detail & Related papers  (2023-12-22T11:56:22Z)
• NutritionVerse-Real: An Open Access Manually Collected 2D Food Scene Dataset for Dietary Intake Estimation [68.49526750115429]
  We introduce NutritionVerse-Real, an open access manually collected 2D food scene dataset for dietary intake estimation. The NutritionVerse-Real dataset was created by manually collecting images of food scenes in real life, measuring the weight of every ingredient and computing the associated dietary content of each dish.
  arXiv  Detail & Related papers  (2023-11-20T11:05:20Z)
• Towards the Creation of a Nutrition and Food Group Based Image Database [58.429385707376554]
  We propose a framework to create a nutrition and food group based image database. We design a protocol for linking food group based food codes in the U.S. Department of Agriculture's (USDA) Food and Nutrient Database for Dietary Studies (FNDDS) Our proposed method is used to build a nutrition and food group based image database including 16,114 food datasets.
  arXiv  Detail & Related papers  (2022-06-05T02:41:44Z)
• MyFood: A Food Segmentation and Classification System to Aid Nutritional Monitoring [1.5469452301122173]
  The absence of food monitoring has contributed significantly to the increase in the population's weight. Some solutions have been proposed in computer vision to recognize food images, but few are specialized in nutritional monitoring. This work presents the development of an intelligent system that classifies and segments food presented in images to help the automatic monitoring of user diet and nutritional intake.
  arXiv  Detail & Related papers  (2020-12-05T17:40:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.