用大模型驱动多智能体闭环系统，实现餐级个性化营养管理
A Closed-Loop Multi-Agent System Driven by LLMs for Meal-Level Personalized Nutrition Management
- 通过视觉、对话与状态管理三智能体协同，从照片估算营养并动态调餐
- 在模拟用户测试中达到可比营养估算精度与高效任务规划
- 适合做智能饮食助手研发或个性化健康干预的研究者参考
个性化营养管理旨在根据个体摄入和表型定制饮食建议，但现有系统通常将食物记录、营养分析与推荐分开处理。我们提出下一代移动营养助手，结合基于图像的餐食记录与大模型驱动的多智能体控制器，实现餐级闭环支持。系统协调视觉、对话与状态管理智能体，从照片估算营养并更新每日摄入预算，随后根据用户偏好和饮食限制调整下一餐计划。在SNAPMe餐食图像与模拟用户上的实验显示，系统具备竞争力的营养估算能力、个性化菜单生成效果及高效的任务规划。研究结果证明了多智能体大模型控制在个性化营养中的可行性，并揭示了图像中微量营养素估算及大规模真实世界研究中的开放挑战。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。