# DW-Bench: Benchmarking LLMs on Data Warehouse Graph Topology Reasoning

arXiv: https://arxiv.org/abs/2604.18964 · HTML: https://mlsanity.com/paper/2604.18964/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 5 of 5)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [LLM-FK: Multi-Agent LLM Reasoning for Foreign Key Detection in Large-Scale Complex Databases](https://mlsanity.com/paper/2603.07278/) (2026)

## Abstract (arXiv)

This paper introduces DW-Bench, a new benchmark that evaluates large language models (LLMs) on graph-topology reasoning over data warehouse schemas, explicitly integrating both foreign-key (FK) and data-lineage edges. The benchmark comprises 1,046 automatically generated, verifiably correct questions across five schemas. Experiments show that tool-augmented methods substantially outperform static approaches but plateau on hard compositional subtypes.