Towards the AI Historian: Agentic Information Extraction from Primary Sources

TL;DR

This paper introduces the first module of Chronos, an AI Historian that enables historians to extract data from primary sources via natural language, allowing adaptable workflows and iterative refinement.

Contribution

It presents an open-source module that facilitates flexible, natural-language-based information extraction from primary sources for historical research.

Findings

The module supports heterogeneous source corpora.

Historians can evaluate AI model performance on specific tasks.

The system allows iterative workflow refinement through natural language.

Abstract

AI is supporting, accelerating, and automating scientific discovery across a diverse set of fields. However, AI adoption in historical research remains limited due to the lack of solutions designed for historians. In this technical progress report, we introduce the first module of Chronos, an AI Historian under development. This module enables historians to convert image scans of primary sources into data through natural-language interactions. Rather than imposing a fixed extraction pipeline powered by a vision-language model (VLM), it allows historians to adapt workflows for heterogeneous source corpora, evaluate the performance of AI models on specific tasks, and iteratively refine workflows through natural-language interaction with the Chronos agent. The module is open-source and ready to be used by historical researchers on their own sources.