让大模型像侦探一样在图结构中自主探索推理，显著提升图任务表现。
AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
- 用强化学习驱动大模型在图上多尺度导航，结合图原生工具进行探索
- 在节点分类上最高提升17.5%，链接预测提升28.4%，超越现有方法
- 适合研究图神经网络与大模型融合的学者，尤其关注自主推理场景
大型语言模型（LLMs）日益依赖代理能力——迭代检索、工具使用和决策——以突破静态参数化知识的局限。然而现有代理框架将外部信息视为非结构化文本，未能利用真实数据中的拓扑依赖关系。为此，我们提出代理图学习（AGL），将图学习重构为拓扑感知导航与基于大模型推理的交织过程。具体地，我们提出AgentGL，首个基于强化学习（RL）的AGL框架。AgentGL赋予大模型代理图原生工具以实现多尺度探索，通过搜索约束思维调控工具使用，在准确性和效率间取得平衡，并采用图条件课程强化学习策略，无需逐步监督即可稳定长程策略学习。在多个文本属性图（TAG）基准和多种大模型骨干上，AgentGL显著优于强基线图语言模型（GraphLLM）和GraphRAG，节点分类绝对提升最高达17.5%，链接预测提升最高达28.4%。结果表明，AGL是使大模型自主导航并推理复杂关系环境的有前景方向。代码已公开于https://github.com/sunyuanfu/AgentGL。
原文摘要 · Abstract (English)
Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as unstructured text and fail to leverage the topological dependencies inherent in real-world data. To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference. Specifically, we propose AgentGL, the first reinforcement learning (RL)-driven framework for AGL. AgentGL equips an LLM agent with graph-native tools for multi-scale exploration, regulates tool usage via search-constrained thinking to balance accuracy and efficiency, and employs a graph-conditioned curriculum RL strategy to stabilize long-horizon policy learning without step-wise supervision. Across diverse Text-Attributed Graph (TAG) benchmarks and multiple LLM backbones, AgentGL substantially outperforms strong GraphLLMs and GraphRAG baselines, achieving absolute improvements of up to 17.5% in node classification and 28.4% in link prediction. These results demonstrate that AGL is a promising frontier for enabling LLMs to autonomously navigate and reason over complex relational environments. The code is publicly available at https://github.com/sunyuanfu/AgentGL.
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。