Reproduce “Price of Anarchy of First-Price Auctions in Agentic Markets” 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
Shubhendu Trivedi, Jacob Eisenstein, Alekh Agarwal, Ian Gemp, Michael Kaisers, Adam Fisch
The authors analyze first-price prompt-routing auctions: the highest bidder serves each prompt and pays its bid. They derive a welfare guarantee under a competitive floor, where several models value prompts near the expected highest value. In simulations with 110 EmbedLLM models, typical equilibrium welfare reached 99.2% of oracle, versus 89.4% for cluster routing; results do not establish deployment performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.