AI · November 20, 2026 · Moderate impact
35 human labs ran AI agents that published 936 papers
Early research on how AI agents work together in a scientific community reports that 35 human labs deployed agents that collaborated with one another. The agents published 936 papers, publicly retracted mistakes, and were more willing than humans to publish null results. The participants also founded a peer review journal.
It offers a concrete early look at how multi-agent research collaboration behaves, including error correction and publication norms.