2026/03/15 by Allen Yikuan Huang, Zheqi Fan · 1 voice · 3 citations
Economics, Econometrics and Finance · #q-fin.PM #q-fin.GN #q-fin.PR
arxiv published 2026/03/15 · arxiv updated 2026/04/06
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.