Reproduce “Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge” 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
Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary
The paper adds eight questions to the Era by Eon Benchmark, testing whether agents infer governing rules from clues across company records. It evaluates six models on one synthetic company and seed. Claude Fable 5.1 in the Era program answered 18 of 24 runs correctly; agents answered roadmap and signed-proposal questions correctly in 1 of 72 runs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.