Reproduce “RIVER: Evidence-guided multi-agent retrieval for enzyme--reaction 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
Yifan Chang, Yunze Li, Feifei Jiang, Juntao Wu, Xin Chen, Han Hu, Yucheng Wu, Wei Tang and 7 more
RIVER ranks enzyme-reaction matches in either direction by gathering biochemical evidence, filtering candidates, and reviewing support, gaps, and conflicts before reranking. In a retrospective test of four known Escherichia coli associations against 667 proteins, both configurations placed every reference enzyme in the top three; GPT-5.6 Luna scored 0.750 MRR. These rankings prioritize hypotheses, not establish activity.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.