Towards Agentic Schema Refinement
Agapi Rissaki, Ilias Fountalis, Nikolaos Vasiloglou, Wolfgang, Gatterbauer
TL;DR
This paper introduces a multi-agent LLM-based approach to automatically discover and refine semantic views in complex enterprise databases, improving data interpretability for analytical tasks.
Contribution
It presents a novel multi-agent LLM simulation method for iterative schema refinement through collaborative view definition, enhancing database usability.
Findings
Effective LLM-based view discovery demonstrated
Improved interpretability of complex databases
Facilitates LLM-powered database exploration
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation
MethodsSparse Evolutionary Training