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

TL;DR

GraphChain enhances large language models' ability to analyze large-scale graphs by using dynamic tool sequences and adaptive strategies, overcoming context and reasoning limitations.

Contribution

The paper introduces a novel framework combining progressive graph distillation and structure-aware adaptation to improve LLM-based graph analysis.

Findings

Outperforms prior methods in large-scale graph tasks

Enables scalable and adaptive graph analysis with LLMs

Efficiently tailors tool strategies to diverse graph structures

Abstract

Large Language Models (LLMs) face significant limitations when applied to large-scale graphs, struggling with context constraints and inflexible reasoning. We present GraphChain, a framework that enables LLMs to analyze complex graphs through dynamic sequences of specialized tools, mimicking human exploratory intelligence. Our approach introduces two key innovations: (1) Progressive Graph Distillation, a reinforcement learning mechanism that generates optimized tool sequences balancing task relevance with information compression, and (2) Structure-aware Test-Time Adaptation, which efficiently tailors tool selection strategies to diverse graph topologies using spectral properties and lightweight adapters without costly retraining. Experiments show GraphChain significantly outperforms prior methods, enabling scalable and adaptive LLM-driven graph analysis.