Reproduce “DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery” 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
Yuxing Chen, Zhisheng Zhang, Cheng Tang, Wei Li, Minghui Zhang, Ziyan Huang, Shaocong Wei, Jiawei Chen and 15 more
DrugHarness turns execution experience into evidence-backed, conditional scientific guidance, which an independent agent reviews and later feedback can revise. In retrospective in-domain MolBench evaluation with frozen skills, Qwen affinity-comparison accuracy rose from 62.2% to 81.1%, and optimization success from 79.5% to 87.2%. This does not establish transfer to unseen targets or task families.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.