The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management
This work addresses the challenge of automating complex investment decisions for institutional investors, representing an incremental advancement by applying agentic AI to a specific domain.
The paper tackles the problem of institutional asset management by introducing an agentic AI pipeline where specialized agents produce capital market assumptions, construct portfolios using multiple methods, and vote on outputs, with a meta-agent improving performance based on past forecasts, resulting in a system that autonomously manages portfolios under human oversight.
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.