Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning
This work addresses the problem of zero-shot graph learning for researchers and practitioners by introducing a novel method that leverages explicit reasoning, though it is incremental in combining existing reasoning models with graph tasks.
The paper tackled the challenge of generalizing to unseen graph tasks without supervision by proposing Graph-R1, a GNN-free approach that reformulates graph tasks as textual reasoning problems solved by Large Reasoning Models, and it outperformed state-of-the-art baselines in zero-shot settings.
Generalizing to unseen graph tasks without task-pecific supervision remains challenging. Graph Neural Networks (GNNs) are limited by fixed label spaces, while Large Language Models (LLMs) lack structural inductive biases. Recent advances in Large Reasoning Models (LRMs) provide a zero-shot alternative via explicit, long chain-of-thought reasoning. Inspired by this, we propose a GNN-free approach that reformulates graph tasks--node classification, link prediction, and graph classification--as textual reasoning problems solved by LRMs. We introduce the first datasets with detailed reasoning traces for these tasks and develop Graph-R1, a reinforcement learning framework that leverages task-specific rethink templates to guide reasoning over linearized graphs. Experiments demonstrate that Graph-R1 outperforms state-of-the-art baselines in zero-shot settings, producing interpretable and effective predictions. Our work highlights the promise of explicit reasoning for graph learning and provides new resources for future research.