Autonomous Scientific Discovery
Overview
The field studies how AI can move beyond answering questions to uncovering patterns, mechanisms, equations, and useful experiments across mathematics, physics, biology, and materials science. Approaches include symbolic regression and sparse equation identification, active learning and Bayesian experiment selection, and LLM-based agents that coordinate coding, simulation, literature review, or laboratory work. Evaluation increasingly uses executable benchmarks, held-out data, formal proofs, and experimental validation to check both results and the evidence behind them. Systems can handle well-specified workflows, but open-ended insight, reliable mechanism claims, identifiability, and reproducibility remain difficult, motivating stronger verification and human oversight.
Latest papers
128 papers22 papers in the last four weeks, up 47% on the four weeks before. 0.1% of all new papers.