Search-on-Graph-R1: Training LLMs to Navigate Knowledge Graphs with Reinforcement Learning
Researchers present Search-on-Graph-R1, a method for training an 8B parameter language model to answer knowledge graph questions by internalizing graph navigation skills. The approach combines supervised fine-tuning and reinforcement learning, using a frontier teacher guided by gold SPARQL queries to generate grounded trajectories. Search-on-Graph-R1 achieves state-of-the-art results on the CWQ benchmark and outperforms larger frozen models on several datasets, without relying on auxiliary modules or LLM judges during training or inference.
Why it matters: This work shows that smaller, efficiently trained models can match or surpass much larger systems in knowledge graph question answering, potentially lowering deployment costs and complexity.
Full story at: arXiv Computation and Language ↗