让图数据库能自动提问、推理和学习，实现智能数据管理
Top Ten Challenges Towards Agentic Neural Graph Databases
- 引入自主构建查询、神经执行与持续学习能力
- 提出十项关键技术挑战，推动图数据库智能化
- 适合需要自适应数据处理的智能系统开发者
图数据库（GDBs）如Neo4j和TigerGraph在处理关联数据方面表现优异，但缺乏高级推理能力。神经图数据库（NGDBs）通过集成图神经网络（GNNs）实现对不完整或噪声数据的预测分析与推理。然而，现有NGDBs依赖预定义查询，缺乏自主性与适应性。本文提出代理式神经图数据库（Agentic NGDBs），在NGDBs基础上新增三项核心功能：自主查询构造、神经查询执行与持续学习。我们识别出实现该目标的十大关键挑战，包括语义单元表示、归纳推理、可扩展查询执行以及与大语言模型（LLMs）等基础模型的集成。通过解决这些挑战，Agentic NGDBs有望为现代数据驱动应用提供智能、自我优化的数据管理系统，推动自适应与自治数据管理的发展。
原文摘要 · Abstract (English)
Graph databases (GDBs) like Neo4j and TigerGraph excel at handling interconnected data but lack advanced inference capabilities. Neural Graph Databases (NGDBs) address this by integrating Graph Neural Networks (GNNs) for predictive analysis and reasoning over incomplete or noisy data. However, NGDBs rely on predefined queries and lack autonomy and adaptability. This paper introduces Agentic Neural Graph Databases (Agentic NGDBs), which extend NGDBs with three core functionalities: autonomous query construction, neural query execution, and continuous learning. We identify ten key challenges in realizing Agentic NGDBs: semantic unit representation, abductive reasoning, scalable query execution, and integration with foundation models like large language models (LLMs). By addressing these challenges, Agentic NGDBs can enable intelligent, self-improving systems for modern data-driven applications, paving the way for adaptable and autonomous data management solutions.
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。