AutoScientists puts a decentralized AI lab on autopilot
Researchers just introduced AutoScientists, a decentralized multi-agent system designed for long-running scientific experimentation. Instead of relying on a rigid central planner, agents self-organize into teams, vet ideas before burning compute, and share failures to avoid redundant runs. It optimized GPT training 1.9x faster than Autoresearch while topping previous agents across biomedical benchmarks.