让大模型通过推理解决未见图任务，无需额外训练。
Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning
- 将图任务转为文本推理，用大模型直接求解。
- 在零样本下超越现有方法，准确率显著提升。
- 提供带推理路径的图数据集，适合研究新范式。
在无特定任务监督的情况下泛化到未见图任务仍具挑战。图神经网络受限于固定标签空间，而大语言模型缺乏结构归纳偏置。近期大型推理模型（LRMs）通过显式长链思维推理提供了零样本替代方案。受此启发，我们提出一种无需图神经网络的方法，将节点分类、链接预测和图分类任务重构为由大型推理模型解决的文本推理问题。我们构建了首个包含详细推理轨迹的图任务数据集，并开发了Graph-R1，一个利用任务特定重思模板引导线性化图推理的强化学习框架。实验表明，Graph-R1在零样本设置下优于现有最先进基线，生成可解释且有效的预测。本工作凸显了显式推理在图学习中的潜力，并为未来研究提供了新资源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。