NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering
This work addresses nutrition question answering for personalized dietary guidance, offering a domain-specific incremental improvement in multi-agent reasoning.
The paper tackles the challenges of limited reasoning capacity and contextual overload in nutrition question answering by introducing NG-Router, a graph-supervised multi-agent collaboration framework that integrates agents into knowledge graphs and uses a graph neural network for routing. It shows consistent performance improvements over single-agent and ensemble baselines across multiple benchmarks.
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.