A key difference in how AI agents collaborate compared to humans is their ability to run multiple discussions in parallel, altering configurations such as which agent speaks first or removing a critic...

Prompt optimization techniques were not able to help multi-agent teams break through the "synergy gap," where a team is unable to perform significantly better than its best individual member.

The SleepFM model found that brain activity signals during REM sleep are particularly predictive of future risks for dementia, stroke, heart disease, and kidney issues.

Research found that expert AI agents can be overly polite and accommodating to other agents, which leads to a degradation of the overall team's performance.

AI agents in the Virtual Lab project designed nanobodies that, after experimental validation, proved more effective in many cases than some previously human-designed nanobodies.

The SleepFM model, trained on nearly 600,000 hours of multi-modal sleep data from 65,000 people, can predict over 100 different future diseases from a single night of sleep recording.

A training paradigm called "Learning to Discover," which prioritizes aggressive exploration over imitation, enabled open-source models to achieve some of the best-known solutions in math and optimizat...