Beyond Prompting: An Autonomous Framework for Systematic Factor Investing via Agentic AI

TL;DR

This paper introduces an autonomous, self-directed AI framework for systematic factor investing that generates interpretable trading signals and demonstrates high performance in the U.S. equity market.

Contribution

It presents a novel autonomous AI system that formulates trading signals endogenously, reducing manual intervention and enhancing scalability and interpretability.

Findings

Long-short portfolios achieved an annualized Sharpe ratio of 3.11.

The approach yielded a 59.53% return in the U.S. equity market.

The system mitigates data snooping biases through strict validation.

Abstract

This paper develops an autonomous framework for systematic factor investing via agentic AI. Rather than relying on sequential manual prompts, our approach operationalizes the model as a self-directed engine that endogenously formulates interpretable trading signals. To mitigate data snooping biases, this closed-loop system imposes strict empirical discipline through out-of-sample validation and economic rationale requirements. Applying this methodology to the U.S. equity market, we document that long-short portfolios formed on the simple linear combination of signals deliver an annualized Sharpe ratio of 3.11 and a return of 59.53%. Finally, our empirics demonstrate that self-evolving AI offers a scalable and interpretable paradigm.