Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition
Nutri-ATLAS grounds nutrition advice in USDA graphs, hybrid retrieval, and robot-observed food availability.
Nutri-ATLAS is an embodied nutrition agent that combines a Food-Nutrient knowledge graph from USDA FoodData Central and FoodKG, 64-dimensional GATv2 embeddings, hybrid graph-text retrieval, and robot-based evidence gathering. It supports nutrient extraction, gap filling, substitutes, and recipe-level meal composition while updating dietary and food-availability memory. On HealthyFoodSubs the hybrid retriever scores 37.9% MAP, 80.7% RR@5, and 90.1% RR@10. On PFoodReQ it reaches 78.8% MAP, 83.0% MAR, and 77.5% F1, and NutriBench v2 tests nine quantized Qwen3.5-9B configurations.
- Builds a Food-Nutrient graph from USDA FoodData Central and FoodKG
- Learns 64-dimensional GATv2 food and recipe embeddings
- Hybrid retriever reaches 37.9% MAP and 90.1% RR@10
- PFoodReQ results are 78.8% MAP, 83.0% MAR, and 77.5% F1
- Nutrient estimates use nine quantized Qwen3.5-9B configurations
Full article219 words · extracted from arxiv.org · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.32803