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.

Vanilla graph databases are pretty much everywhere thanks to the ever-growing graphs in production, flexible graph data models, and expressive query languages. Query engines assume that graphs in classical graph DBs are complete. Under the completeness assumption, we can build indexes, store the graphs in a variety of read/write-optimized formats and expect the DB would return what is there. But this assumption does not often hold in practice (we'd say, doesn't hold way too often). If we look at some prominent knowledge graphs (KGs): in Freebase, 93.8% of people have no place of birth and 78.5% have no nationality, about 68% of people do not have any profession, while in Wikidata, about 50% of artists have no date of birth, and only 0.4% of known buildings have information about height.