Reproduce “Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization” 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

Zhenwei Tang, Di Bai, Jintao Liu, Xidong Wu, Qianfeng Wen, Xinwu Cheng

The study examines how seller agents rewrite tool listings and affect buyer choices in simulated Amazon and Instagram markets. Researchers executed tools beforehand to check whether a selected tool returned the requested field. All five tested seller model-and-harness combinations inflated claims, but only one brought Amazon success near random: 29–31%, against 88–89% originally. Listings remained within the simulation.

Summary by alphaXiv.

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