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

DevFeed: [Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery](<https://devfeed.tech/articles/empirical-research-assistance-era-from-nature-publication-to-catalyzing-computational-discovery-6765.md>)

Original publisher: [Read original article](<https://research.google/blog/empirical-research-assistance-era-from-nature-publication-to-catalyzing-computational-discovery/>)

Published: 2026-05-19T17:52:00Z

Content type: news

Language: en

Sources: [The latest research from Google](<https://devfeed.tech/sources/the-latest-research-from-google.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [coding](<https://devfeed.tech/topics/coding.md>), [Google](<https://devfeed.tech/topics/google.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Data Science](<https://devfeed.tech/topics/data-science.md>), [Software](<https://devfeed.tech/topics/software.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>), [Mathematics](<https://devfeed.tech/topics/mathematics.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [drive](<https://devfeed.tech/tags/drive.md>), [general-science](<https://devfeed.tech/tags/general-science.md>), [google](<https://devfeed.tech/tags/google.md>), [machine-intelligence](<https://devfeed.tech/tags/machine-intelligence.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [open-source-models-datasets](<https://devfeed.tech/tags/open-source-models-datasets.md>), [time-series](<https://devfeed.tech/tags/time-series.md>)

## AI overview

Google Research introduces Empirical Research Assistance (ERA), an AI tool that uses Gemini to write and optimize scientific code. ERA searches literature, explores solutions, evaluates results, and uses tree search to optimize code for computational experiments. Tests across genomics, public health, satellite imagery, neuroscience, time-series forecasting, and mathematics show expert-level benchmark performance. ERA also helped build the Computational Discovery prototype, which is being made available through Google Labs and Gemini for Science.

## Source excerpt

General Science