An LLM Workflow That Reproduces, Improves, and Extends Published Economics Research

We introduce an open-source workflow that enables an LLM to reproduce, improve, and extend an economics article using the article’s published replication package. First, the workflow attempts to reproduce the original calculations, checks for discrepancies with published findings, and performs automated sensitivity analysis. Across 4,452 published replication packages for five economics journals, the workflow flags discrepancies in 3,460 articles or their appendices. Second, the workflow improves the original calculations by using a different implementation or algorithm. In 496 articles, the workflow is able to reduce a calculation’s computation time, at similar or greater accuracy, by more than a factor of 10. Third, the workflow extends the original analysis. In 923 articles, the workflow develops an extension that does not appear in the original article and that is aligned with the original article’s goals and assumptions.