Top Ten Challenges Towards Agentic Neural Graph Databases
This work addresses the problem of limited inference capabilities in graph databases for data management applications, but it is incremental as it builds on existing Neural Graph Databases.
The paper tackles the lack of autonomy and adaptability in Neural Graph Databases by introducing Agentic Neural Graph Databases, which add autonomous query construction, neural query execution, and continuous learning to enable intelligent, self-improving systems for data-driven applications.
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.