In recent years, a variety of data-driven evolutionary algorithms (DDEAs) have been proposed to solve time-consuming and computationally intensive optimization problems. DDEAs are usually divided into offline DDEAs and online DDEAs, with offline DDEAs being the most widely studied and proven to display excellent performance. However, most offline DDEAs suffer from three disadvantages. First, they require many surrogates to build a relatively accurate model, which is a process that is redundant and time-consuming. Second, when the available fitness evaluations are insufficient, their performance tends to be not entirely satisfactory. Finally, to cope with the second problem, many algorithms use data generation methods, which significantly increases the algorithm runtime. To overcome these problems, we propose a brand-new DDEA with radial basis function networks as its surrogates. First, we invented a fast data generation algorithm based on clustering to enlarge the dataset and reduce fitting errors. Then, we trained radial basis function networks and carried out adaptive design for their parameters. We then aggregated radial basis function networks using a unique model management framework and demonstrated its accuracy and stability. Finally, fitness evaluations were obtained and used for optimization. Through numerical experiments and comparisons with other algorithms, this algorithm has been proven to be an excellent DDEA that suits data optimization problems.

Optical tweezers (OT), a cornerstone of micromanipulation, are fundamentally constrained by substrate-induced adhesion and friction, limiting their application to mesoscale objects and fragile biological specimens where overcoming these resistive forces requires physiologically damaging laser powers. Here, we overcome this long-standing challenge by introducing dielectric levitation optical tweezers (DL-OT), a multiphysics platform that seamlessly integrates alternating-current dielectric levitation with optical traps. By using negative dielectrophoresis (n-DEP) to actively neutralize the normal force, DL-OT eliminates solid – solid contact and near-wall viscous drag. Crucially, we demonstrate the fundamental superiority of this active physical levitation over traditional passive antiadhesion coatings. This physical decoupling enables the smooth translation of large biological samples using low, biologically safe optical powers (~15 mW) rather than nonviable levels (>150 mW). The creation of this frictionless environment not only boosts the maximum manipulation speed of standard microtargets by 40% but also enables the stable optical transport of previously intractable mesoscale objects (100 to 260 μm), including microgears and shrimp eggs. By preventing photothermal damage and mechanical deformation, DL-OT demonstrates very good biocompatibility, significantly enhancing cell viability postmanipulation. Building upon these advantages, we demonstrate advanced on-chip biofabrication protocols through the targeted, high-precision assembly of multicellular spheroids and the safe transport of patient-derived organoids, followed by their success in situ culture. By transforming OT from a microscale tool into a mesoscale assembly platform, DL-OT paves the way for breakthroughs in tissue engineering, regenerative medicine, and the bottom – up assembly of living systems.