A conference just tested AI agents’ ability to do science

In a first, a scientific conference welcomed paper submissions from any area of science, but with one catch: AI had to do most of the work. Called Agents4Science 2025, the Oct. 22 virtual event focused on the work of artificial intelligence agents — systems that pair large language models with other tools or databases to perform multistep tasks.

From formulating hypotheses to analyzing data and providing the first round of peer reviews, AI agents took the lead. Human reviewers then stepped in to assess the top submissions. In all, 48 papers out of 314 made the cut. Each had to detail how people and AI collaborated on every stage

→ Continue reading at Science News

More from author

Related posts

Advertisment

Latest posts

Author talks about Russia’s attempt to create a ‘sovereign internet’

For years, the Kremlin has been cracking down on the internet. It has banned Facebook and Instagram. Now, it's pushing a new app...

Napoleon’s retreating army may have been plagued by these microbes

Meghan Rosen is a senior writer who reports on the life sciences for Science News. She earned a Ph.D. in biochemistry and molecular...

Brain cancer can dissolve parts of the skull

Meghan Rosen is a senior writer who reports on the life sciences for Science News. She earned a Ph.D. in biochemistry and molecular...