Reproduce “Scaling the Scholar: Distributed Multi-Agent System for Automated Peer Review” 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
Kamil Szczepanik, Oskar Swat, Bartłomiej Karbownik, Jędrzej Kozak, Aliaksandr Pryimak
Scaling the Scholar predicts editorial decisions by sending papers to five verdict agents assessing distinct criteria and four diagnostics that do not affect verdicts. An orchestrator combines agent scores and applies venue-specific guidelines. On 297 ICLR 2025 papers, it reports AUC 0.91 versus 0.75 for Stanford’s system, but it predicts past decisions, not review quality.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.