Reproduce “ReviewPilot: A Multi-Agent System for Screening and Data Extraction in Systematic Reviews” 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

Zhaoqian Xue, Shaoze Zhou, Xuexin Li, Junting Mu, Haozheng Liu, Zhongyin Wang, Yichun He, Renkai Ma and 5 more

ReviewPilot turns systematic reviews into a configurable, inspectable workflow in which researchers confirm criteria and extraction fields, while agents screen studies and extract values with reasons and quoted passages. Project memory preserves settings and corrections. On evaluated PERG pools, it outperformed AgentSLR on reported screening and extraction metrics, but single-run results do not establish performance on unseen reviews.

Summary by alphaXiv.

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