Reproduce “Strategic Multi-Agent Resource Allocation via Statistical Contracts” 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

Ben Chugg, Michael I. Jordan, Aaditya Ramdas

The authors develop an evidence-based allocation rule that uses e-values to distribute resources among entrants. It limits each null agent’s expected allocation to its entry cost and controls the expected share allocated to null agents, without requiring independence. In experiments, the simpler region Q had median relative optimality gaps of 2.9% and 6.2% at σᵥ = 0.8; these are not universal guarantees.

Summary by alphaXiv.

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