AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning

TL;DR

AgentGL introduces a reinforcement learning framework that enables large language models to perform topology-aware graph learning, improving reasoning and navigation over complex relational data.

Contribution

It is the first RL-driven framework for agentic graph learning that leverages graph-native tools and curriculum strategies to enhance LLM capabilities in graph reasoning.

Findings

AgentGL outperforms existing GraphLLMs and GraphRAG baselines.

Achieves up to 17.5% improvement in node classification.

Achieves up to 28.4% improvement in link prediction.

Abstract

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.