Towards Agentic Schema Refinement

Agapi Rissaki, Ilias Fountalis, Nikolaos Vasiloglou, Wolfgang Gatterbauer

Keywords: LLMs, multi-agent simulation, schema refinement, data exploration, data semantics

Abstract: Large enterprise databases can be complex and messy, obscuring the data semantics needed for analytical tasks. We propose a semantic layer in-between the database and the user as a set of small and easy-to-interpret database views, effectively acting as a refined version of the schema. To discover these views, we introduce a multi-agent Large Language Model (LLM) simulation where LLM agents collaborate to iteratively define and refine views with minimal input. Our approach paves the way for LLM-powered exploration of unwieldy databases.

Submission Number: 69