用语义规划替代直接生成查询，让大图数据分析更高效准确。
GraphSeek: Next-Generation Graph Analytics with LLMs
- 通过语义目录规划代替直接生成查询，分离推理与执行
- 小上下文LLM下成功率提升至86%，优于增强版LangChain
- 适合需要处理复杂大规模图数据的开发者和分析师
图数据在各领域基础广泛，但缺乏专业知识难以使用。尽管大语言模型（LLMs）能通过自然语言实现图分析，但在处理工业级属性图时效率低下：数据量大、异构性强、结构复杂且动态演化。为此，我们提出一种新型抽象，用于复杂多查询图分析。核心思想是将直接从自然语言生成图查询的脆弱过程，替换为基于描述图模式与操作的语义目录进行规划。具体而言，该设计实现了语义平面（用于LLM规划与推理）与执行平面（用于数据库级确定性查询执行）的清晰分离。此架构在小上下文LLM下仍显著提升令牌效率与任务成功率。基于此抽象，我们构建了首个增强型图分析框架GraphSeek。GraphSeek在多个任务中取得更高成功率（如达86%），展现出下一代可负担、易用的图分析前景，融合了大模型推理与数据库级执行能力，适用于大规模复杂属性图。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。