Reproduce “DrugCoding: A Scientific Programming Agent for 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
Junwei Hu, Zhuohao Lin, Kun Li, Hengnan Zhang
DrugCoding coordinates computational drug-discovery tasks by turning research requests into dependency-aware plans, routing model recommendations, binding eligible models, and checking structured tool calls. On 1,250 multi-turn benchmark sessions, its configured pipeline achieved 97.35% session-level Pass@1, versus 88.11% for Codex. This measures exact reference-matching submissions, not successful scientific execution or validated scientific outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.