Honegumi: An Interface for Accelerating the Adoption of Bayesian Optimization in the Experimental Sciences

Abstract Bayesian optimization (BO) is increasingly used for experimental design in materials science, chemistry, and biology, yet existing libraries and underlying concepts can be complex for non-machine-learning experts. To address this barrier, we introduce Honegumi, an interactive tool that simplifies creating advanced Bayesian optimization scripts. Honegumi provides a dynamic selection grid for configuring options and automatically generates ready-to-use, unit-tested Python scripts tailored to specific needs. In addition to the interface, a suite of materials-focused tutorials offers both conceptual background and practical guidance, bridging theory and implementation. Built on the Ax platform, Honegumi leverages state-of-the-art BO methods while restructuring the user experience to make advanced techniques more accessible to experimental researchers. By lowering the barrier to entry and providing educational resources, Honegumi aims to accelerate the adoption of advanced BO across scientific domains. The tool is available at https://honegumi.readthedocs.io/ and as a flexible Python package, extensible to other applications.