Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition
On the map: LLM agents and tool use → Medical and scientific domain agents
Abstract (arXiv)
Generative and Agentic IoT systems offer a promising foundation for digital healthcare applications that combine sensing, personalized reasoning, and autonomous interaction in real-world environments. Nutrition assistance is a natural use case, but existing Large Language Model (LLM)-based systems are often limited to passive text interaction and static context, making them unreliable when food descriptions are ambiguous or nutritional evidence is missing. We propose Nutri-ATLAS, an Embodied Agent for Tabulated Lookup and Assistance for smarter nutrition in the real world. It integrates graph-grounded nutrition reasoning, hardware-aware LLM selection, and robot-based evidence acquisition. Nutri-ATLAS builds a unified Food-Nutrient knowledge graph from USDA FoodData Central and FoodKG and learns 64-dimensional GATv2 food and recipe embeddings. A shared hybrid graph-text scoring mechanism supports food nutrition extraction, nutritional gap filling, substitute retrieval, and recipe-level meal composition, while an LLM-guided skill interface navigates landmarks, updates dietary-context and food-accessibility memory, and grounds recommendations in observed food availability. We evaluate Nutri-ATLAS across nutrient estimation, substitution retrieval, recipe recommendation, patient-profile adherence, edge deployment, and real-world embodied execution. On HealthyFoodSubs, the hybrid retriever achieves 37.9% MAP, 80.7% RR@5, and 90.1% RR@10. On NutriBench v2, Dense+GAT retrieval grounds nutrient estimation across nine quantized Qwen3.5-9B configurations. On PFoodReQ, Nutri-ATLAS reaches 78.8% MAP, 83.0% MAR, and 77.5% F1. A patient-profile study shows adherence to allergy and healthy-target constraints for all selected cases.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 72 references that are in the map. First posted on arXiv 26 Sep 2026.
Builds on
28 of 72 references.
References · 28
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2017Graph Attention Networkscited by 8,854
- 2016Layer Normalizationcited by 5,579
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2015Fast R-CNNcited by 2,930
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
- 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
- 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
- 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
- 2021How Attentive are Graph Attention Networks?cited by 818
- 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
16 more
- 2024SliceGPT: Compress Large Language Models by Deleting Rows and Columnscited by 378
- 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agentscited by 213
- 2025EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agentscited by 55
- 2024ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Frameworkcited by 20
- 2021Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graphcited by 17
- 2024NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal Descriptionscited by 17
- 2024NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoningcited by 16
- 2025Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video Understandingcited by 13
- 2025NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherencecited by 7
- 2024TinyM2Net-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deploymentcited by 4
- 2025HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Modelscited by 4
- 2025MedMambaLite: Hardware-Aware Mamba for Medical Image Classificationcited by 4
- 2025ATLASv2: LLM-Guided Adaptive Landmark Acquisition and Navigation on the Edgecited by 3
- 2026A Closed-Loop Multi-Agent System Driven by LLMs for Meal-Level Personalized Nutrition Managementcited by 2
- 2026An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food Recommendationscited by 1
- 2026NutriMLLM: Multimodal Large Language Models for Dietary Micronutrient Analysiscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management
- 2026Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition
- 2026FAM-Bench: A Multimodal Benchmark for Condition-Aware Food-as-Medicine Reasoning
- 2026OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice
- 2025Introducing the Swiss Food Knowledge Graph: AI for Context-Aware Nutrition Recommendation
- 2025Food4All: An Agentic Framework and Benchmark for Food Resource Navigation with Adaptive User Understanding
- 2026NutriOrion: A Hierarchical Multi-Agent Framework for Personalized Nutrition Intervention Grounded in Clinical Guidelines
- 2026CGU-ILALab at FoodBench-QA 2026: Comparing Traditional and LLM-based Approaches for Recipe Nutrient Estimation