LLM Agents for Combinatorial Efficient Frontiers: Investment Portfolio Optimization

TL;DR

This paper introduces a novel agentic framework for combinatorial portfolio optimization, specifically addressing the CCPO problem, and demonstrates its effectiveness in matching state-of-the-art algorithms while reducing workflow complexity.

Contribution

The study develops a new agentic framework for CCPO that automates complex workflows and matches top algorithms, simplifying portfolio optimization processes.

Findings

Framework matches state-of-the-art algorithms

Reduces effort in workflow and algorithm development

Maintains acceptable error levels in complex problems

Abstract

Investment portfolio optimization is a task conducted in all major financial institutions. The Cardinality Constrained Mean-Variance Portfolio Optimization (CCPO) problem formulation is ubiquitous for portfolio optimization. The challenge of this type of portfolio optimization, a mixed-integer quadratic programming (MIQP) problem, arises from the intractability of solutions from exact solvers, where heuristic algorithms are used to find approximate portfolio solutions. CCPO entails many laborious and complex workflows and also requires extensive effort pertaining to heuristic algorithm development, where the combination of pooled heuristic solutions results in improved efficient frontiers. Hence, common approaches are to develop many heuristic algorithms. Agentic frameworks emerge as a promising candidate for many problems within combinatorial optimization, as they have been shown to be equally efficient with regard to automating large workflows and have been shown to be excellent in terms of algorithm development, sometimes surpassing human-level performance. This study implements a novel agentic framework for the CCPO and explores several concrete architectures. In benchmark problems, the implemented agentic framework matches state-of-the-art algorithms. Furthermore, complex workflows and algorithm development efforts are alleviated, while in the worst case, lower but acceptable error is reported.