NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Kaiwen, Zhang, Zheyuan, Yuan, Zhengqing, Murugesan, Keerthiram, Galass, Vincent, Zhang, Chuxu, Ye, Yanfang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909837082755072
author Shi, Kaiwen
Zhang, Zheyuan
Yuan, Zhengqing
Murugesan, Keerthiram
Galass, Vincent
Zhang, Chuxu
Ye, Yanfang
author_facet Shi, Kaiwen
Zhang, Zheyuan
Yuan, Zhengqing
Murugesan, Keerthiram
Galass, Vincent
Zhang, Chuxu
Ye, Yanfang
contents Diet plays a central role in human health, and Nutrition Question Answering (QA) offers a promising path toward personalized dietary guidance and the prevention of diet-related chronic diseases. However, existing methods face two fundamental challenges: the limited reasoning capacity of single-agent systems and the complexity of designing effective multi-agent architectures, as well as contextual overload that hinders accurate decision-making. We introduce Nutritional-Graph Router (NG-Router), a novel framework that formulates nutritional QA as a supervised, knowledge-graph-guided multi-agent collaboration problem. NG-Router integrates agent nodes into heterogeneous knowledge graphs and employs a graph neural network to learn task-aware routing distributions over agents, leveraging soft supervision derived from empirical agent performance. To further address contextual overload, we propose a gradient-based subgraph retrieval mechanism that identifies salient evidence during training, thereby enhancing multi-hop and relational reasoning. Extensive experiments across multiple benchmarks and backbone models demonstrate that NG-Router consistently outperforms both single-agent and ensemble baselines, offering a principled approach to domain-aware multi-agent reasoning for complex nutritional health tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering
Shi, Kaiwen
Zhang, Zheyuan
Yuan, Zhengqing
Murugesan, Keerthiram
Galass, Vincent
Zhang, Chuxu
Ye, Yanfang
Computation and Language
Diet plays a central role in human health, and Nutrition Question Answering (QA) offers a promising path toward personalized dietary guidance and the prevention of diet-related chronic diseases. However, existing methods face two fundamental challenges: the limited reasoning capacity of single-agent systems and the complexity of designing effective multi-agent architectures, as well as contextual overload that hinders accurate decision-making. We introduce Nutritional-Graph Router (NG-Router), a novel framework that formulates nutritional QA as a supervised, knowledge-graph-guided multi-agent collaboration problem. NG-Router integrates agent nodes into heterogeneous knowledge graphs and employs a graph neural network to learn task-aware routing distributions over agents, leveraging soft supervision derived from empirical agent performance. To further address contextual overload, we propose a gradient-based subgraph retrieval mechanism that identifies salient evidence during training, thereby enhancing multi-hop and relational reasoning. Extensive experiments across multiple benchmarks and backbone models demonstrate that NG-Router consistently outperforms both single-agent and ensemble baselines, offering a principled approach to domain-aware multi-agent reasoning for complex nutritional health tasks.
title NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering
topic Computation and Language
url https://arxiv.org/abs/2510.09854