CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents

arXiv:2512.01089v2 Announce Type: replace Abstract: Automated Scientific Discovery (ASD) systems can help automatically generate and run code-based experiments, but their capabilities are limited by the code they can reliably generate from parametric knowledge alone. As a result, current systems either mutate a small number of manually-crafted experiment examples, or operate solely from parametric knowledge, limiting quality and reach. We introduce CodeDistiller, a system that automatically dist