# DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling

arXiv: https://arxiv.org/abs/2604.06474 · HTML: https://mlsanity.com/paper/2604.06474/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 119 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024)
- [DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research](https://mlsanity.com/paper/2511.19399/) (2025)
- [DiscoveryBench: Towards Data-Driven Discovery with Large Language Models](https://mlsanity.com/paper/2407.01725/) (2024)
- [BLADE: Benchmarking Language Model Agents for Data-Driven Science](https://mlsanity.com/paper/2408.09667/) (2024)
- [Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data](https://mlsanity.com/paper/2402.17644/) (2024)
- [DataSciBench: An LLM Agent Benchmark for Data Science](https://mlsanity.com/paper/2502.13897/) (2025)
- [DeepAnalyze: Agentic Large Language Models for Autonomous Data Science](https://mlsanity.com/paper/2510.16872/) (2025)
- [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://mlsanity.com/paper/2408.15232/) (2024)
- [ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration](https://mlsanity.com/paper/2502.00675/) (2025)
- [DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis](https://mlsanity.com/paper/2508.20033/) (2025)
- [InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation](https://mlsanity.com/paper/2407.06423/) (2024)
- [Deep Research Bench: Evaluating AI Web Research Agents](https://mlsanity.com/paper/2506.06287/) (2025)
- [Benchmarking Data Science Agents](https://mlsanity.com/paper/2402.17168/) (2024)
- [SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions](https://mlsanity.com/paper/2407.11417/) (2024)
- [Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis](https://mlsanity.com/paper/2402.01386/) (2024)
- [RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery](https://mlsanity.com/paper/2503.00751/) (2025)
- [OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking](https://mlsanity.com/paper/2501.09751/) (2025)
- [FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data](https://mlsanity.com/paper/2509.02473/) (2025)
- [An LLM-Based Approach for Insight Generation in Data Analysis](https://mlsanity.com/paper/2503.11664/) (2025)
- [SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL](https://mlsanity.com/paper/2601.17699/) (2026)
- [Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models](https://mlsanity.com/paper/2602.02039/) (2026)
- [The Case of the Mysterious Citations](https://mlsanity.com/paper/2602.05867/) (2026)
- [InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents](https://mlsanity.com/paper/2511.22884/) (2025)

## Built on by (most cited first, 7 of 7)

- [FinResearchBench II: A Deep Research Benchmark with Consensus-Derived Gold Rubrics for Distinguishing Financial Report Quality](https://mlsanity.com/paper/2607.12252/) (2026)
- [Unsupervised Skill Discovery for Agentic Data Analysis](https://mlsanity.com/paper/2606.06416/) (2026)
- [Discovery Agents for Real-Time Analytics: Toward Proactive Insight Systems](https://mlsanity.com/paper/2605.27571/) (2026)
- [Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories](https://mlsanity.com/paper/2606.11176/) (2026)
- [Benchmarking Hybrid Deep Research Across Database Querying and Web Search](https://mlsanity.com/paper/2609.09410/) (2026)
- [Fail Loudly: An Auditable Runtime for Agentic Data Analysis](https://mlsanity.com/paper/2609.32528/) (2026)
- [Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses](https://mlsanity.com/paper/2609.35255/) (2026)

## Abstract (arXiv)

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.