Researchers have developed a multi-agent trading system called ContestTrade. The system uses two teams: a Data Team that processes market data and a Research Team that makes trading decisions. A 'Quantify-Predict-Allocate' mechanism is used to score agent outputs, predict future utility, and allocate resources. In a test, ContestTrade performed better than baseline systems in terms of return and risk-adjusted performance. --- Why it matters: This matters because it shows how AI can be used to improve trading decisions in financial markets, potentially leading to increased efficiency and profitability. Source: https://arxiv.org/abs/2508.00554