MASS: Muli-agent simulation scaling for portfolio construction

TL;DR

This paper introduces MASS, a multi-agent simulation framework for direct portfolio construction that adapts to market changes and demonstrates that increasing agent numbers improves excess returns, outperforming existing methods.

Contribution

MASS is a novel end-to-end multi-agent simulation framework that dynamically learns agent distributions for improved portfolio construction.

Findings

Scaling agents up to 512 increases excess returns.

MASS outperforms seven state-of-the-art baselines.

Framework is robust and validated on Chinese A-share market data.

Abstract

The application of LLM-based agents in financial investment has shown significant promise, yet existing approaches often require intermediate steps like predicting individual stock movements or rely on predefined, static workflows. These limitations restrict their adaptability and effectiveness in constructing optimal portfolios. In this paper, we introduce the Multi-Agent Scaling Simulation (MASS), a novel framework that leverages multi-agent simulation for direct, end-to-end portfolio construction. At its core, MASS employs a backward optimization process to dynamically learn the optimal distribution of heterogeneous agents, enabling the system to adapt to evolving market regimes. A key finding enabled by our framework is the exploration of the scaling effect for portfolio construction: we demonstrate that as the number of agents increases exponentially (up to 512), the aggregated decisions yield progressively higher excess returns. Extensive experiments on a challenging, self-collected dataset from the 2023 Chinese A-share market show that MASS consistently outperforms seven state-of-the-art baselines. Further backtesting, stability analyses and the experiment on data leakage concerns validate its enhanced profitability and robustness. We have open-sourced our code, dataset, and training snapshots at https://github.com/gta0804/MASS/ to foster further research.