3 papers
physics.chem-ph2026
RECOB: Reliable Benchmarking of Experimental Optimization in Chemistry and Materials Science
Zikai Xie, Jiaming Wan, Linjiang Chen
Optimization methods for experimental science are often evaluated on synthetic functions that are reproducible but omit important characteristics of real experiments. We introduce…
cs.AI2026
Language models guide symbolic equation discovery by controlling search
Zikai Xie, Wenmei Li, Man Luo +2
Scientific equation discovery must combine broad domain priors with strict numerical testing. Symbolic regression supplies numerical grounding but faces a combinatorial search spac…
cs.LG2026
Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial
Zhongwei Yu, Rasul Tutunov, Alexandre Max Maraval +13
Traditional scientific discovery relies on an iterative hypothesise-experiment-refine cycle that has driven progress for centuries, but its intuitive, ad-hoc implementation often w…