Reproduce “Born for the Task: Rethinking Quantum Chemistry with Foresighted Agentic Computing” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Haozhi Han, Junjie Yang, Ruge Zhang, Zihe Huang, Pengyi Xu, Bo Zhang, Xianyi Zhang, Yunquan Zhang and 4 more

MakoBORN predicts which algorithms and numerical settings meet accuracy and resource limits for Gaussian-basis Hartree–Fock, then guides coding agents in generating a specialized program. On a B-DNA duplex, it completes in 8.1 hours on one node with one A100 GPU, versus a predicted 1,400 hours for a general-purpose baseline; both reported molecular calculations meet the stated error tolerance.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.