# MASS: Muli-agent simulation scaling for portfolio construction arXiv: https://arxiv.org/abs/2505.10278 ยท HTML: https://mlsanity.com/paper/2505.10278/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. - Builds on 27 of its 52 references that are in the map. - First posted on arXiv 15 May 2025. ## Placed in - LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/) ## Builds on (most cited first, 27 of 27) - [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020) - [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023) - [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023) - [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023) - [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024) - [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023) - [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024) - [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023) - [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024) - [A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist](https://mlsanity.com/paper/2402.18485/) (2024) - [FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making](https://mlsanity.com/paper/2407.06567/) (2024) - [Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning](https://mlsanity.com/paper/2503.16252/) (2025) - [Qlib: An AI-oriented Quantitative Investment Platform](https://mlsanity.com/paper/2009.11189/) (2020) - [TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets](https://mlsanity.com/paper/2502.01506/) (2025) - [HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information](https://mlsanity.com/paper/2110.13716/) (2021) - [AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay](https://mlsanity.com/paper/2502.16789/) (2025) - [Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning](https://mlsanity.com/paper/2306.12964/) (2023) - [Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models](https://mlsanity.com/paper/2402.03659/) (2024) - [MASTER: Market-Guided Stock Transformer for Stock Price Forecasting](https://mlsanity.com/paper/2312.15235/) (2023) - [MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model](https://mlsanity.com/paper/2409.07486/) (2024) - [AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors](https://mlsanity.com/paper/2406.18394/) (2024) - [When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments](https://mlsanity.com/paper/2407.18957/) (2024) - [The SocialAI School: Insights from Developmental Psychology Towards Artificial Socio-Cultural Agents](https://mlsanity.com/paper/2307.07871/) (2023) - [MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization](https://mlsanity.com/paper/2210.01774/) (2022) - [Stock Price Correlation Coefficient Prediction with ARIMA-LSTM Hybrid Model](https://mlsanity.com/paper/1808.01560/) (2018) - [Learning Universal Multi-level Market Irrationality Factors to Improve Stock Return Forecasting](https://mlsanity.com/paper/2502.04737/) (2025) - [CausalStock: Deep End-to-end Causal Discovery for News-driven Stock Movement Prediction](https://mlsanity.com/paper/2411.06391/) (2024) ## Built on by (most cited first, 9 of 9) - [ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism](https://mlsanity.com/paper/2508.00554/) (2025) - [QuantEvolve: Automating Quantitative Strategy Discovery through Multi-Agent Evolutionary Framework](https://mlsanity.com/paper/2510.18569/) (2025) - [PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management](https://mlsanity.com/paper/2605.27887/) (2026) - [MEME: Modeling the Evolutionary Modes of Financial Markets](https://mlsanity.com/paper/2602.11918/) (2026) - [Hierarchical AI Multi-Agent Fundamental Investing: Evidence from China's A-Share Market](https://mlsanity.com/paper/2510.21147/) (2025) - [SCSimulator: An Exploratory Visual Analytics Framework for Partner Selection in Supply Chains through LLM-driven Multi-Agent Simulation](https://mlsanity.com/paper/2601.14566/) (2026) - [GeomHerd: A Forward-looking Herding Quantification via Ricci Flow Geometry on Agent Interactive Simulations](https://mlsanity.com/paper/2605.11645/) (2026) - [Can Agentic Trading Systems Pay for Their Own Intelligence?](https://mlsanity.com/paper/2607.10286/) (2026) - [SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes](https://mlsanity.com/paper/2609.19705/) (2026) ## Abstract (arXiv) 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.