An AI system to help scientists write expert-level empirical software
Authors: Eser Aygün, Anastasiya Belyaeva, Gheorghe Comanici, Marc Coram, Hao Cui, Jake Garrison, Renee Johnston Anton Kast, Cory Y. McLean, Zahra Shamsi, David Smalling, Subhashini Venugopalan, Sarah Martinson, Martyna Beata Płomecka, Lai Wei, Qian-Ze Zhu, Erica Brand, Anna Bulanova, Jeffrey A. Cardille, Chris Co, Scott Ellsworth, Ryan Krueger, Johan Kartiwa, Daniel J. Liebling, Jan-Matthis Lueckmann, Paul Raccuglia, Wang, Katherine Chou, James Manyika, Yossi Matias, John C. Platt, Shibl Mourad, Michael P. Brenner
Journal: Nature
Publication year: 2026
DOI: 10.1038/s41586-026-10658-6
Abstract
Abstract The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments. To address this, we present 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) to systematically improve the quality metric and intelligently navigate the large space of possible solutions. The system achieves expert-level results when it explores and integrates complex research ideas from external sources. The effectiveness of tree search is demonstrated across a wide range of benchmarks. In bioinformatics, it discovered 40 novel methods for single-cell data analysis that outperformed the top human-developed methods on a public leaderboard. In epidemiology, it generated 14 models that outperformed the CDC ensemble and all other individual models for forecasting COVID-19 hospitalizations. Our method also produced state-of-the-art software for geospatial analysis, neural activity prediction in zebrafish, time series forecasting and numerical solution of integrals. By devising and implementing novel solutions to diverse tasks, the system represents a significant step towards accelerating scientific progress.