AI Insight
Researchers developed ERA (Empirical Research Assistance), an AI system that combines a Large Language Model with Tree Search algorithms to autonomously generate scientific software aimed at optimizing a defined quality metric. The system was tested across multiple scientific domains, including bioinformatics, epidemiology, geospatial analysis, neuroscience, and numerical mathematics. In benchmark evaluations, ERA produced results competitive with or superior to top human-developed methods, including outperforming CDC ensemble models for COVID-19 hospitalization forecasting and surpassing leading methods on a public single-cell data analysis leaderboard.
Why it matters
Automated generation of research-grade scientific software could substantially reduce the time and expertise required to conduct computational experiments, potentially accelerating discovery cycles across a broad range of scientific fields. This approach may also lower barriers to entry for researchers lacking advanced programming skills in specialized domains.
arXiv:2509.06503v3 Announce Type: replace-cross
Abstract: The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experimentscite{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.
Source: An AI system to help scientists write expert-level empirical software