Reproduce “An Agentic Approach to Metadata Reasoning” 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

Jiani Zhang, Sercan O. Arik, Cosmin Arad, Fatma Ozcan, Alon Halevy

Metadata Reasoner helps an analytics agent select data tables by translating a question into requirements, searching candidates, inspecting summaries, and using targeted tools to check values and joinability. On KramaBench, its Harness Plugin reaches 88.63% selection F1, versus 77.90% for Agentic SQL. This measures table selection, not end-to-end answer accuracy; runtime-dependent selection is tested on a limited task set.

Summary by alphaXiv.

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