Autonomous Experimentation
Overview
Autonomous experimentation studies how to close the loop between proposing a question, choosing an experiment, collecting results, and using them to guide the next step, in both physical laboratories and computational research. Common approaches include Bayesian optimization and active learning for selecting measurements, reinforcement learning and evolutionary search for control, and language-model agents that plan protocols and coordinate instruments or code. These methods can make costly or slow settings—such as materials synthesis, microscopy, chemistry, and machine-learning model development—more systematic and efficient. Real-world demonstrations are growing, but reliable execution, safety, evidence validation, and sustained improvement remain difficult; benchmarks increasingly test complete experimental trajectories rather than plans or final scores alone.
Latest papers
148 papers26 papers in the last four weeks, up 86% on the four weeks before. 0.2% of all new papers.