# Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization

arXiv: https://arxiv.org/abs/2609.11141 · HTML: https://mlsanity.com/paper/2609.11141/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 8 of 8)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Judge's Verdict: A Comprehensive Analysis of LLM Judge Capability Through Human Agreement](https://mlsanity.com/paper/2510.09738/) (2025)
- [NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization](https://mlsanity.com/paper/2406.17961/) (2024)
- [Database Normalization via Dual-LLM Self-Refinement](https://mlsanity.com/paper/2508.17693/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy database-level constraints. We study this issue through database normalization, involving reasoning about functional dependencies, lossless join decompositions, and inter-table constraints. We introduce a Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF. DNBENCH uses a three-axis protocol to measure semantic equivalence, structural accuracy, and logical validity. Across Single, Complex, and Real World levels, DNBENCH uncovers recurring failures in dependency inference, schema decomposition, and inter-table constraint reconstruction. We further propose Multi-Agent Reasoning for Schemas (MARS), which separates evidence extraction, violation diagnosis, and decomposition planning from schema generation and verification. MARS improves the DNB-SCORE by 82.0% over the single-prompt baseline. All artifacts will be released upon acceptance.