# Chronos: The AI Co-Historian

arXiv: https://arxiv.org/abs/2604.03553 · HTML: https://mlsanity.com/paper/2604.03553/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 57 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning](https://mlsanity.com/paper/2501.00321/) (2024)
- [Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study](https://mlsanity.com/paper/2305.13062/) (2023)
- [CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy](https://mlsanity.com/paper/2412.02210/) (2024)
- [Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction](https://mlsanity.com/paper/2410.21169/) (2024)
- [OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning](https://mlsanity.com/paper/2505.17163/) (2025)
- [READoc: A Unified Benchmark for Realistic Document Structured Extraction](https://mlsanity.com/paper/2409.05137/) (2024)
- [Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin](https://mlsanity.com/paper/1809.05501/) (2018)
- [DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding](https://mlsanity.com/paper/2508.08589/) (2025)
- [American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers](https://mlsanity.com/paper/2308.12477/) (2023)
- [Efficient OCR for Building a Diverse Digital History](https://mlsanity.com/paper/2304.02737/) (2023)
- [CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition](https://mlsanity.com/paper/2509.19768/) (2025)
- [Newswire: A Large-Scale Structured Database of a Century of Historical News](https://mlsanity.com/paper/2406.09490/) (2024)
- [SCORE: A Semantic Evaluation Framework for Generative Document Parsing](https://mlsanity.com/paper/2509.19345/) (2025)
- [Deep Learning for Economists](https://mlsanity.com/paper/2407.15339/) (2024)
- [A Benchmark of Nested Named Entity Recognition Approaches in Historical Structured Documents](https://mlsanity.com/paper/2302.10204/) (2023)
- [Structuring Authenticity Assessments on Historical Documents using LLMs](https://mlsanity.com/paper/2407.09290/) (2024)
- [Multimodal LLMs for Historical Dataset Construction from Archival Image Scans: German Patents (1877-1918)](https://mlsanity.com/paper/2512.19675/) (2025)
- [GutenOCR: A Grounded Vision-Language Front-End for Documents](https://mlsanity.com/paper/2601.14490/) (2026)
- [OmniOCR: Generalist OCR for Ethnic Minority Languages](https://mlsanity.com/paper/2602.21042/) (2026)
- [Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directories](https://mlsanity.com/paper/2302.08948/) (2023)

## Abstract (arXiv)

AI is increasingly supporting, accelerating, and automating scientific discovery across subjects. Yet, the adoption of AI in historical research remains limited due to the lack of specialised solutions for historians. To change this, we introduce Chronos, an AI Co-Historian designed to support historians. It allows researchers to create and customize research workflows through natural-language interaction and share these as Chronos-Extensions with others. Chronos specifically addresses the need of historians for a tool that is specialised, non-technical, highly customizable, and facilitates extensive task evaluation. As a first extension, we introduce Chronos-Extract, which enables researchers to automate the targeted extraction of information from image scans of historical sources. We benchmark Chronos-Extract on three historical source corpora and find that it achieves high task-accuracy across primary sources spanning three centuries and diverse languages, layouts, and typefaces. Chronos is openly available and ready for historians to use on their own primary and secondary sources.