Designing Agentic AI-Based Screening for Portfolio Investment

TL;DR

This paper presents an agentic AI platform for portfolio management that combines LLM-based screening and advanced statistical methods to improve investment performance, demonstrating superior Sharpe ratios on S&P 500 data.

Contribution

It introduces a novel multi-layer AI architecture for asset screening and portfolio optimization, with a theoretical analysis of screening errors and their impact on performance metrics.

Findings

Achieves higher Sharpe ratios than baseline portfolios.

Demonstrates effective asset screening with LLM agents.

Provides theoretical guarantees under mild screening errors.

Abstract

We introduce a new agentic artificial intelligence (AI) platform for portfolio management. Our architecture consists of three layers. First, two large language model (LLM) agents are assigned specialized tasks: one agent screens for firms with desirable fundamentals, while a sentiment analysis agent screens for firms with desirable news. Second, these agents deliberate to generate and agree upon buy and sell signals from a large portfolio, substantially narrowing the pool of candidate assets. Finally, we apply a high-dimensional precision matrix estimation procedure to determine optimal portfolio weights. A defining theoretical feature of our framework is that the number of assets in the portfolio is itself a random variable, realized through the screening process. We introduce the concept of sensible screening and establish that, under mild screening errors, the squared Sharpe ratio of the screened portfolio consistently estimates its target. Empirically, our method achieves superior Sharpe ratios relative to an unscreened baseline portfolio and to conventional screening approaches, evaluated on S&P 500 data over the period 2020--2024.