{"ID":2857765,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.09854","arxiv_id":"2510.09854","title":"NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering","abstract":"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.","short_abstract":"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 com...","url_abs":"https://arxiv.org/abs/2510.09854","url_pdf":"https://arxiv.org/pdf/2510.09854v1","authors":"[\"Kaiwen Shi\",\"Zheyuan Zhang\",\"Zhengqing Yuan\",\"Keerthiram Murugesan\",\"Vincent Galass\",\"Chuxu Zhang\",\"Yanfang Ye\"]","published":"2025-10-10T20:38:33Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Graph Neural Network\"]","has_code":false}