Problem
Research questions and friction points this paper is trying to address.
dietary nutrition planning
personalized constraints
multiobjective optimization
chronic disease management
ShanLiangRen: A Nutrition Agent for Personalized Daily Meal Planning
🤖 AI Summary
This study addresses the practical challenges in personalized dietary planning arising from conflicts between user constraints and multidimensional nutritional objectives, as well as dynamic feedback. To this end, this work proposes a personalized multi-objective meal planning agent and introduces the first fully quantified formulation of the dietary planning problem. Specifically, natural language requirements are transformed into constraint instances, while retrieval-augmented generation narrows the candidate solution space. Subsequently, large language models iteratively optimize meal plans guided by Pareto principles. The primary contribution lies in establishing an end-to-end closed-loop pipeline that translates natural language inputs into executable, precise meal plans, yielding quantified recipes with specific ingredient portions alongside compliance reports. The proposed system has been successfully deployed as a WeChat Mini Program application.
📝 Abstract
Dietary nutrition planning plays an important role in chronic disease management and maintaining a healthy body. In applications, it must simultaneously satisfy personalized constraints and reasonable multidimensional nutritional goals. These two aspects often conflict, and user constraints evolve with feedback, resulting in a substantial gap between generic guidelines and executable plans. To bridge this gap, we first propose the personalized fully quantified multiobjective dietary planning problem (MDP). To tackle MDP, we develop a nutrition agent, ShanLiangRen. The system first transforms dietary specifications, nutrient data, user attributes and natural language requirements into an individualized constrained planning instance. It then employs an exact retrieval-augmented generation method to shrink the feasible candidate set from a large scale ingredient and recipe space. Finally, it adopts a refinement guided by Pareto principles, where an LLM iteratively revises candidate plans under deterministic nutrition computation and feedback from constraint verification. The system outputs fully quantified meal plans with explicit ingredients and portion sizes, together with reports on nutrition compliance that show constraint satisfaction and nutrient interval attainment. We have released the system online as a WeChat Program, ShanLiangRen. A demo video is available at https://www.youtube.com/watch?v=652OtY5VlGA.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multiobjective Dietary Planning
Nutrition Agent
Retrieval-Augmented Generation
Pareto-guided Refinement
Large Language Model
🔎 Similar Papers
No similar papers found.
