AI 自己改进了化学计算里的优化器
化学计算里最烧时间的不是算结果，而是反复调整分子结构的那几千步。这篇让 AI 当研究员，直接改写优化器本身，目标是少算几步。它从目前最快的开源优化器 Sella 出发，自己迭代出两个新版本，在没见过的分子和计算模型上，都能稳定省下 23% 到 60% 的算力，而且精度不变。最狠的是，AI 全程没碰过 DFT 梯度，纯靠理解优化逻辑就做到了。这不是你明天能用的工具，但它指向一个趋势：AI 不再只是被调用的模型，而是能改进科学计算底层算法的研究者。
📄 原文摘要(英文)
Geometry optimization is a major cost in many quantum-chemical workflows: each optimization step requires one force evaluation, and at the density-functional level that evaluation dominates the wall time. Research in this area has produced a broad range of optimization methods, and we ask whether a language model can improve on the best of them through autoresearch. An agent rewrites the optimizer itself to minimize force-call counts, restrained by two admission gates that reject premature stopping and improvements that do not generalize to unseen molecules. Starting from Sella, the fastest open-source optimizer available, the search produces AutoSella, a family of two optimizers. Both of them deliver consistent force-call reductions relative to Sella across held-out molecular benchmarks and potentials not used during the search. Most notably, at the r2SCAN-3c DFT level, the best variant requires only 40.2--77.2% of Sella's force calls while achieving the same energy reduction, even though agent used no DFT gradients.