跳到正文
arXiv cs.AI· Haozhi Han, Junjie Yang, Ruge Zhang, Zihe Huang, Pengyi Xu, Bo Zhang, Xianyi Zhang, Yunquan Zhang, Ting Cao, Yunxin Liu, Yifeng Chen, Kun Li·· 2 小时前AI 评分43

MakoBORN:面向量子化学的前瞻式智能体计算框架

Born for the Task: Rethinking Quantum Chemistry with Foresighted Agentic Computing

AI 导读

研究团队提出 MakoBORN,一种前瞻式智能体计算框架,可按需合成高性能量子化学程序。它在执行前预测各策略的精度与运行时间,从精度-时间 Pareto 前沿中选出满足误差容限的最快方案并指导 coding agents 编译。

正文 · 原文

Authors:Haozhi Han, Junjie Yang, Ruge Zhang, Zihe Huang, Pengyi Xu, Bo Zhang, Xianyi Zhang, Yunquan Zhang, Ting Cao, Yunxin Liu, Yifeng Chen, Kun Li

View PDF HTML (experimental)

Abstract:Quantum chemistry relies on general-purpose software, whose generality leaves many large-scale calculations beyond practical resource budgets. Coding agents make task-specific programs cheap to write, but not efficient ones easy to find: whether a computational strategy is accurate and fast enough becomes clear only after it actually runs at the target scale. We introduce MakoBORN, a foresighted agentic computing framework that synthesizes high performance quantum chemistry programs on demand. MakoBORN anticipates the behavior of each strategy before execution, extrapolating its error from representative small systems and predicting its runtime from the target-scale workload and measured hardware throughputs. Building on these predictions, MakoBORN unfolds the preset schemes of existing packages into independently configurable algorithmic components, selects the fastest strategy within the error tolerance from the predicted accuracy-runtime Pareto frontier, and guides coding agents to compile it with component-level performance predictions. For a Hartree-Fock calculation with 50,024 basis functions, MakoBORN finishes in 1.41 h on a single CPU node, 77$\times$ faster than the estimated runtime of a general-purpose baseline and still 9.8$\times$ faster with development time included. On a single GPU, MakoBORN completes the ubiquitin calculation in 2.1 h, the same order of runtime as the GPU-accelerated package Mako on 64 GPUs, and shortens the B-DNA duplex calculation from an estimated two months to 8.1 h (173$\times$).
Subjects: Artificial Intelligence (cs.AI); Chemical Physics (physics.chem-ph)
Cite as: arXiv:2611.22897 [cs.AI]
  (or arXiv:2611.22897v2 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.22897

arXiv-issued DOI via DataCite

Submission history

From: Haozhi Han [view email]
[v1] Tue, 17 Nov 2026 15:05:38 UTC (2,286 KB)
[v2] Wed, 18 Nov 2026 13:07:39 UTC (2,285 KB)

来源:arXiv cs.AI · arxiv.org