DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling
This addresses the challenge for researchers and analysts who need to perform data-centric research on structured databases, offering a novel approach that integrates exploratory data analysis and data storytelling, though it builds on existing LLM agent paradigms.
The paper tackles the problem of conducting deep research over large-scale structured databases, which requires iterative hypothesis generation and quantitative reasoning, by presenting DataSTORM, an LLM-based agentic system that achieves a 19.4% relative improvement in insight-level recall and 7.2% in summary-level score on InsightBench, and outperforms proprietary systems like ChatGPT Deep Research on a new ACLED dataset.
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.