Epstein Files Engine: Agentic Search for Investigative Journalism
Not on the map. Why?
Abstract (arXiv)
On Jan. 30, 2026, the U.S. Department of Justice released a mixed-media collection concerning Jeffrey Epstein, including about three million pages of PDFs. We describe the Epstein Files Engine, an A.I. agent The New York Times deployed to investigate the files. The Engine translated reporter questions into Google BigQuery SQL queries across three corpora: Epstein-related releases, the Times's archive and external, Epstein-related news headlines. It used an LLM to plan queries and returned citation-rich answers a reporter could verify and trust. More than 100 journalists used the Engine, and it contributed to at least 20 published stories. We report how reporters queried it and describe Diff, our text-and-visual duplicate matching method that amplified novelty signals and allowed the Engine to surface genuinely new information. We argue that newsroom agents serve newsrooms best not as autonomous writers, but as interfaces to source material and institutional knowledge.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 30 references that are in the map. First posted on arXiv 24 Sep 2026.
Builds on
6 of 30 references.
References · 6
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
- 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
- 2024Using Generative Agents to Create Tip Sheets for Investigative Data Reportingcited by 1
- 2025On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Searchcited by 1
- 2026EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledgecited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025How can AI agents support journalists' work? An experiment with designing an LLM-driven intelligent reporting system
- 2026Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
- 2025Auditing LLM Editorial Bias in News Media Exposure
- 2026Agents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic Control
- 2025Benchmarking Agentic Newswriting via Journalistic Workflows
- 2026Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research
- 2026Follow the Entities: A Corpus Map for Agentic Search
- 2026Deep-Research Agents Can Be Poisoned via User-Generated Content