GraphSeek: Next-Generation Graph Analytics with LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911514173112320 |
|---|---|
| author | Besta, Maciej Jarmocik, Łukasz Hrycyna, Orest Klaiman, Shachar Mączka, Konrad Gerstenberger, Robert Müller, Jürgen Nyczyk, Piotr Niewiadomski, Hubert Hoefler, Torsten |
| author_facet | Besta, Maciej Jarmocik, Łukasz Hrycyna, Orest Klaiman, Shachar Mączka, Konrad Gerstenberger, Robert Müller, Jürgen Nyczyk, Piotr Niewiadomski, Hubert Hoefler, Torsten |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11052 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GraphSeek: Next-Generation Graph Analytics with LLMs Besta, Maciej Jarmocik, Łukasz Hrycyna, Orest Klaiman, Shachar Mączka, Konrad Gerstenberger, Robert Müller, Jürgen Nyczyk, Piotr Niewiadomski, Hubert Hoefler, Torsten Databases Artificial Intelligence Computation and Language Human-Computer Interaction Information Retrieval 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. |
| title | GraphSeek: Next-Generation Graph Analytics with LLMs |
| topic | Databases Artificial Intelligence Computation and Language Human-Computer Interaction Information Retrieval |
| url | https://arxiv.org/abs/2602.11052 |