DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling
Abstract
Deep research with Large Language Model (LLM) agents is emerging as a powerful paradigm for multi-step information discovery, synthesis, and analysis. However, existing approaches primarily focus on unstructured web data, while the challenges of conducting deep research over large-scale structured databases remain relatively underexplored. Unlike web-based research, effective data-centric research requires more than retrieval and summarization and demands iterative hypothesis generation, quantitative reasoning over structured schemas, and convergence toward a coherent analytical narrative. In this paper, we present DataSTORM, an LLM-based agentic system capable of autonomously conducting research across both large-scale structured databases and internet sources. Grounded in principles from Exploratory Data Analysis and Data Storytelling, DataSTORM reframes deep research over structured data as a thesis-driven analytical process: discovering candidate theses from data, validating them through iterative cross-source investigation, and developing them into coherent analytical narratives. We evaluate DataSTORM on InsightBench, where it achieves a new state-of-the-art result with a 19.4% relative improvement in insight-level recall and 7.2% in summary-level score. We further introduce a new dataset built on ACLED, a real-world complex database, and demonstrate that DataSTORM outperforms proprietary systems such as ChatGPT Deep Research across both automated metrics and human evaluations.
Cite
@article{arxiv.2604.06474,
title = {DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling},
author = {Shicheng Liu and Yucheng Jiang and Sajid Farook and Camila Nicollier Sanchez and David Fernando Castro Pena and Monica S. Lam},
journal= {arXiv preprint arXiv:2604.06474},
year = {2026}
}