Researchers from Princeton, Ant Group and Stanford Introduce AQuA: A Two-Part Agentic Framework for Autonomous Factor Discovery and Model Development in Quantitative Finance

Researchers from Princeton, Ant Group, and Stanford have introduced AQuA, a framework designed to automate quantitative finance research by separating factor discovery from model development. This structure aims to prevent a common failure in agentic systems where models inadvertently learn from biased or corrupted data produced during their own experimental iterations. By isolating these processes, the framework seeks to improve the reliability of autonomous systems when identifying market trends and developing predictive financial strategies.