GraphSeek: Next-Generation Graph Analytics with LLMs

TL;DR

GraphSeek introduces a novel framework that combines LLM planning with deterministic execution to enable efficient, scalable, and accessible graph analytics on complex, large-scale property graphs.

Contribution

It presents a new abstraction separating LLM planning from execution, enabling effective graph analytics on industry-scale datasets with improved success rates.

Findings

Achieves 86% success rate over enhanced LangChain

Substantially improves token efficiency and task effectiveness

Unifies LLM reasoning with database-grade execution

Abstract

Graphs are foundational across domains but remain hard to use without deep expertise. LLMs promise accessible natural language (NL) graph analytics, yet they fail to process industry-scale property graphs effectively and efficiently: such datasets are large, highly heterogeneous, structurally complex, and evolve dynamically. To address this, we devise a novel abstraction for complex multi-query analytics over such graphs. Its key idea is to replace brittle generation of graph queries directly from NL with planning over a Semantic Catalog that describes both the graph schema and the graph operations. Concretely, this induces a clean separation between a Semantic Plane for LLM planning and broader reasoning, and an Execution Plane for deterministic, database-grade query execution over the full dataset and tool implementations. This design yields substantial gains in both token efficiency and task effectiveness even with small-context LLMs. We use this abstraction as the basis of the first LLM-enhanced graph analytics framework called GraphSeek. GraphSeek achieves substantially higher success rates (e.g., 86% over enhanced LangChain) and points toward the next generation of affordable and accessible graph analytics that unify LLM reasoning with database-grade execution over large and complex property graphs.