arXiv cs.AI· Jeheon Woo·· 10 小时前AI 评分58
AIOA 框架让 AI 智能体自主优化原子模拟数值算法
Autonomous Optimization of Numerical Algorithms by an AI Agent: Application to Atomistic Simulation
AI 导读
研究提出 AIOA 框架，让基于大语言模型的编码智能体在不可修改的校验器约束下循环优化原子模拟数值算法。在 ASE 库上，智能体将六个 kernel 的 Python 实现（NumPy 与 SciPy）平均加速 22-24 倍，结果不变。
正文 · 原文
Abstract:Coding agents built on large language models, run in automated improvement loops, can discover more efficient algorithms. We present AIOA, a framework that brings this approach to the numerical algorithms of atomistic simulation: an agent improves an algorithm against a pre-specified metric in a loop guarded by verifiers it cannot alter. Applied to ASE, a widely used atomistic simulation library, AIOA targets two facets of an algorithm: its implementation, rewritten to run faster with unchanged results, and the method itself, redesigned to converge with fewer force evaluations. Agents made six kernels 22-24 times faster on average in Python with NumPy and SciPy. On unseen problems, optimizers from the best configuration needed 3.1-3.4 times fewer force evaluations than L-BFGS for structure relaxation and 4.6-17 times fewer than standard climbing-image nudged elastic band calculations for reaction paths. The agents' optimizers also contain two algorithmic components we did not find in the literature.
| Comments: | 29 pages, 5 figures, 1 table; Supplementary Information included |
| Subjects: | Chemical Physics (physics.chem-ph); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13143 [physics.chem-ph] |
| (or arXiv:2611.13143v1 [physics.chem-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13143 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jeheon Woo [view email]
[v1]
Mon, 9 Nov 2026 19:23:39 UTC (131 KB)
来源：arXiv cs.AI · arxiv.org