Beyond Prompting: An Autonomous Framework for Systematic Factor Investing via Agentic AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917385099804672 |
|---|---|
| author | Huang, Allen Yikuan Fan, Zheqi |
| author_facet | Huang, Allen Yikuan Fan, Zheqi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14288 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Prompting: An Autonomous Framework for Systematic Factor Investing via Agentic AI Huang, Allen Yikuan Fan, Zheqi Portfolio Management General Finance Pricing of Securities 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. |
| title | Beyond Prompting: An Autonomous Framework for Systematic Factor Investing via Agentic AI |
| topic | Portfolio Management General Finance Pricing of Securities |
| url | https://arxiv.org/abs/2603.14288 |