Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery

Google today published Empirical Research Assistance (ERA), an AI tool that uses Gemini to write and optimize scientific code, in the journal *Nature*. The tool, which achieves expert-level performance across benchmarks in genomics, public health, and mathematics, was used to build the Computational Discovery prototype now available through a trusted tester program in Google Labs. Google also launched related experimental tools, including Hypothesis Generation and Literature Insights, to support different stages of the scientific method.

May 19, 2026 Lizzie Dorfman, Product Manager, and Michael Brenner, Research Scientist, Google Research Published today, Empirical Research Assistance ERA is an AI tool for expert-level scientific coding that helped build the Computational Discovery prototype, now available through a trusted tester program in Google Labs. One of AI’s greatest potential benefits to humanity is increasing the speed and scope of scientific discovery. Empirical Research Assistance ERA , a Google-developed research tool that uses Gemini to write and optimize scientific code, addresses one of the most time-consuming parts of scientific research: iteratively testing and refining computational experiments. It is described in " AI system designed to help scientists write expert-level empirical software https://www.nature.com/articles/s41586-026-10658-6 ”, published today in the journal Nature https://www.nature.com/ . As part of our wider science announcements https://blog.google/innovation-and-ai/technology/research/gemini-for-science-io-2026/ at I/O today, we are also making this technology accessible as a tool that can begin to help scientists around the world. ERA is one of the systems used to build Computational Discovery, a new experimental tool that is starting to roll out more broadly today through Gemini for Science https://ai.google/gemini-for-science/ . We first shared https://research.google/blog/accelerating-scientific-discovery-with-ai-powered-empirical-software/ the design and performance of ERA in the fall, when the preprint was released. Given a scientific problem and a measure of success, ERA can search scientific literature, write code, explore solutions, combine techniques and evaluate the results. ERA considers thousands of options, using a tree search approach to optimize its output code against its given goal. Our Nature publication describes testing ERA on benchmark problems spanning a variety of disciplines: genomics, public health, satellite imagery analysis, neuroscience prediction, a general time-series forecasting benchmark, and mathematics. Results show ERA achieves expert-level performance across all of these benchmarks, potentially democratizing future access to expert-level computational modeling and expanding the capabilities of current experts. Over the past six months, Google Research scientists and our collaborators have been actively experimenting with ERA. In late April, we shared examples of four projects https://research.google/blog/four-ways-google-research-scientists-have-been-using-empirical-research-assistance/ we’d worked on that use ERA to investigate current open problems in science. We now have a total of eight manuscripts https://github.com/google-research/era/tree/main/era applications that apply ERA to specific scientific problems, including the five newly released papers described below. Collectively, these results show how ERA can help drive progress in several domains with immediate scientific impact and public benefit. Today, Google will begin gradually opening access to Computational Discovery http://labs.google/science , built with AlphaEvolve and ERA. We are excited for this new era of scientific discovery enabled by AI-based computational tools, and to further develop them alongside the broader community. Another of the newly launched Gemini for Science experiments is Hypothesis Generation http://labs.google/science , built with AI Co-Scientist, also described in a paper published today https://deepmind.google/blog/co-scientist-a-multi-agent-ai-partner-to-accelerate-research in Nature . Hypothesis Generation and Computational Discovery, as well as the new Literature Insights http://labs.google/science experimental tool, are complementary in their support of different stages of the scientific method. Visit labs.google/science http://labs.google/science to register your interest. We’d like to thank our collaborators, listed on the authors’ list, who helped create ERA , as well as all the scientists who are among the early adopters. Algorithm development underlying ERA was led by Eser Aygun, Gheorghe Comanici and Shibl Mourad . The epidemiological forecasting work is led by Zahra Shamsi, Sarah Martinson, Nicholas Reich, Martyna Plomecka, and Brian Williams. The research on carbon dioxide monitoring is led by Aarón Sonabend-W, Sean Campbell, Renee Johnston, Vishal Batchu, Carl Elkin, Christopher Van Arsdale, John Platt, and Anna Michalak. The paper on runoff forecasting is authored by Ignacio Lopez-Gomez, Michael Brenner, and Tapio Schneider. The manuscript in solar energy engineering is authored by Michael Brenner, Lizzie Dorfman, and John Platt. The research in macroeconomic retail sales forecasting is led by Michael Brenner, Qian-Ze Zhu, Zahra Shamsi, Mette Nielsen, and Paul Raccuglia. We are grateful for leadership support from John Platt, Michael Brenner, Shibl Mourad, Lizzie Dorfman, Vip Gupta, Zoubin Ghahramani, Alison Lentz, Erica Brand, Katherine Chou, Ronit Levavi Morad, Yossi Matias, and James Manyika.