The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ang, Andrew, Azimbayev, Nazym, Kim, Andrey
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918425765347328
author Ang, Andrew
Azimbayev, Nazym
Kim, Andrey
author_facet Ang, Andrew
Azimbayev, Nazym
Kim, Andrey
contents Agentic AI shifts the investor's role from analytical execution to oversight. We present an agentic strategic asset allocation pipeline in which approximately 50 specialized agents produce capital market assumptions, construct portfolios using over 20 competing methods, and critique and vote on each other's output. A researcher agent proposes new portfolio construction methods not yet represented, and a meta-agent compares past forecasts against realized returns and rewrites agent code and prompts to improve future performance. The entire pipeline is governed by the Investment Policy Statement--the same document that guides human portfolio managers can now constrain and direct autonomous agents.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02279
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management
Ang, Andrew
Azimbayev, Nazym
Kim, Andrey
Artificial Intelligence
Multiagent Systems
General Finance
Portfolio Management
91G10, 68T20, 68T37
I.2.1; I.2.6; I.2.7; I.2.11; J.4; H.4.2
Agentic AI shifts the investor's role from analytical execution to oversight. We present an agentic strategic asset allocation pipeline in which approximately 50 specialized agents produce capital market assumptions, construct portfolios using over 20 competing methods, and critique and vote on each other's output. A researcher agent proposes new portfolio construction methods not yet represented, and a meta-agent compares past forecasts against realized returns and rewrites agent code and prompts to improve future performance. The entire pipeline is governed by the Investment Policy Statement--the same document that guides human portfolio managers can now constrain and direct autonomous agents.
title The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management
topic Artificial Intelligence
Multiagent Systems
General Finance
Portfolio Management
91G10, 68T20, 68T37
I.2.1; I.2.6; I.2.7; I.2.11; J.4; H.4.2
url https://arxiv.org/abs/2604.02279