An AI system to help scientists write expert-level empirical software
Abstract
The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments\cite{hannay2009how}. To address this, we present Empirical Research Assistance (ERA), an AI system that creates expert-level scientific software whose goal is to maximize a quality metric. The system uses a Large Language Model (LLM) and Tree Search (TS)\cite{silver2016mastering} to systematically improve the quality metric and intelligently navigate the large space of possible solutions. ERA achieves expert-level results when it explores and integrates complex research ideas from external sources. The effectiveness of tree search is demonstrated across a diverse range of tasks. In bioinformatics, ERA discovered 40 novel methods for single-cell data analysis that outperformed the top human-developed methods on a public leaderboard. In epidemiology, ERA generated 14 models that outperformed the CDC ensemble and all other individual models for forecasting COVID-19 hospitalizations. ERA also produced expert-level software for geospatial analysis, neural activity prediction in zebrafish, and numerical solution of integrals, and a novel rule-based construction for time series forecasting. By devising and implementing novel solutions to diverse tasks, ERA represents a significant step towards accelerating scientific progress.
Cite
@article{arxiv.2509.06503,
title = {An AI system to help scientists write expert-level empirical software},
author = {Eser Aygün and Anastasiya Belyaeva and Gheorghe Comanici and Marc Coram and Hao Cui and Jake Garrison and Renee Johnston Anton Kast and Cory Y. McLean and Peter Norgaard and Zahra Shamsi and David Smalling and James Thompson and Subhashini Venugopalan and Brian P. Williams and Chujun He and Sarah Martinson and Martyna Plomecka and Lai Wei and Yuchen Zhou and Qian-Ze Zhu and Matthew Abraham and Erica Brand and Anna Bulanova and Jeffrey A. Cardille and Chris Co and Scott Ellsworth and Grace Joseph and Malcolm Kane and Ryan Krueger and Johan Kartiwa and Dan Liebling and Jan-Matthis Lueckmann and Paul Raccuglia and Xuefei and Wang and Katherine Chou and James Manyika and Yossi Matias and John C. Platt and Lizzie Dorfman and Shibl Mourad and Michael P. Brenner},
journal= {arXiv preprint arXiv:2509.06503},
year = {2026}
}
Comments
78 pages, 31 figures, 22 tables