GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining

Chunyu Wei, Wenji Hu, Xingjia Hao, Xin Wang, Yifan Yang, Yunhai Wang, Yang Tian, Yueguo Chen

Renmin University of China· Guangxi University· Beijing Jiaotong University

Large Language Model Graph Analysis Tool Learning

Abstract

Large Language Models (LLMs) face significant limitations when applied to large-scale graphs, struggling with context constraints and inflexible reasoning. We introduce GraphChain, a novel framework enabling LLMs to analyze large graphs by orchestrating dynamic sequences of specialized tools, mimicking human exploratory processes.

GraphChain incorporates two core technical contributions:

Progressive Graph Distillation, a reinforcement learning approach that learns to generate tool sequences balancing task relevance and intermediate state compression, thereby overcoming LLM context limitations.
Structure-aware Test-Time Adaptation (STTA), a mechanism using a lightweight, self-supervised adapter conditioned on graph spectral properties to efficiently adapt a frozen LLM policy to diverse graph structures via soft prompts without retraining.

Experiments show GraphChain significantly outperforms prior methods, enabling scalable and adaptive LLM-driven graph analysis.