Towards Agentic Schema Refinement
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.
Cite
Text
Rissaki et al. "Towards Agentic Schema Refinement." NeurIPS 2024 Workshops: TRL, 2024.Markdown
[Rissaki et al. "Towards Agentic Schema Refinement." NeurIPS 2024 Workshops: TRL, 2024.](https://mlanthology.org/neuripsw/2024/rissaki2024neuripsw-agentic/)BibTeX
@inproceedings{rissaki2024neuripsw-agentic,
title = {{Towards Agentic Schema Refinement}},
author = {Rissaki, Agapi and Fountalis, Ilias and Vasiloglou, Nikolaos and Gatterbauer, Wolfgang},
booktitle = {NeurIPS 2024 Workshops: TRL},
year = {2024},
url = {https://mlanthology.org/neuripsw/2024/rissaki2024neuripsw-agentic/}
}