The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management
2026-04-02 • Artificial Intelligence
Artificial IntelligenceMultiagent Systems
AI summaryⓘ
The authors describe a system where many specialized AI agents work together to manage investments. These agents create market predictions, build portfolios using different methods, and review each other's work to improve decisions. One agent even creates new portfolio strategies, while a higher-level agent checks past results to refine the system over time. All activities follow the same investment rules that human managers use, allowing AI to handle oversight rather than detailed analysis.
agentic AIstrategic asset allocationcapital market assumptionsportfolio constructioninvestment policy statementmeta-agentautomated oversightfinancial forecasting
Authors
Andrew Ang, Nazym Azimbayev, Andrey Kim
Abstract
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.