MASS: Multi-Agent Simulation Scaling for Portfolio Construction

2025-05-15

AI Summary

Existing LLM-based multi-agent systems are constrained by purely synthetic simulation or rigid, predefined workflows, limiting their ability to construct robust, alpha-generating portfolios in quantitative investing. This paper proposes MASS (Multi-Agent Simulation Scaling), a novel multi-agent simulation and scaling framework. First, it introduces a scalable multi-agent simulation paradigm that progressively increases agent count to model large-scale market dynamics. Second, it incorporates an end-to-end inverse optimization mechanism that dynamically learns and refines agent specialization, eliminating reliance on handcrafted workflows. Third, it integrates LLM-driven agents, A-share multi-pool backtesting, and systematic sensitivity analysis. Evaluated across three challenging A-share equity pools, MASS consistently outperforms six state-of-the-art baselines. Comprehensive validation—including backtesting, ablation studies, data refresh experiments, and visual diagnostics—confirms substantial improvements in both return stability and persistence. The implementation is publicly available.

Technology Category

• Multiagent Systems: Mechanism Design
• Search and Optimization: Sampling/Simulation-based Search
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

LLM-based multi-agent has gained significant attention for their potential in simulation and enhancing performance. However, existing works are limited to pure simulations or are constrained by predefined workflows, restricting their applicability and effectiveness. In this paper, we introduce the Multi-Agent Scaling Simulation (MASS) for portfolio construction. MASS achieves stable and continuous excess returns by progressively increasing the number of agents for large-scale simulations to gain a superior understanding of the market and optimizing agent distribution end-to-end through a reverse optimization process, rather than relying on a fixed workflow. We demonstrate its superiority through performance experiments, ablation studies, backtesting experiments, experiments on updated data and stock pools, scaling experiments, parameter sensitivity experiments, and visualization experiments, conducted in comparison with 6 state-of-the-art baselines on 3 challenging A-share stock pools. We expect the paradigm established by MASS to expand to other tasks with similar characteristics. The implementation of MASS has been open-sourced at https://github.com/gta0804/MASS.

Problem

• Enhancing portfolio construction via scalable multi-agent simulation
• Overcoming fixed workflow limitations in financial simulations
• Achieving stable excess returns through dynamic agent optimization

Innovation

• LLM-based multi-agent for market simulation
• Reverse optimization for agent distribution
• Progressive agent scaling for excess returns