QuantAgents: Towards Multi-agent Financial System via Simulated Trading

2025-10-06

AI Summary

Existing LLM-based financial agents lack human-like long-term trend forecasting capability, limiting their applicability to real-world fund-level decision-making. Method: We propose a multi-agent collaborative framework comprising four specialized LLM agents—trading analyst, risk control analyst, market news analyst, and portfolio manager—orchestrated via iterative negotiation and a dual-feedback mechanism integrating live performance metrics and simulated forward-looking predictions. Crucially, our system embeds explicit long-term trend modeling directly into the simulated trading loop, overcoming the post-hoc reflection bias inherent in conventional agent architectures. Contribution/Results: In a three-year backtest, our system achieves a cumulative return of 298%, significantly outperforming baseline methods. It demonstrates statistically significant improvements across key metrics—including risk-adjusted returns (e.g., Sharpe ratio), maximum drawdown control, and scenario robustness—validating its efficacy for institutional-grade portfolio management.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

In this paper, our objective is to develop a multi-agent financial system that incorporates simulated trading, a technique extensively utilized by financial professionals. While current LLM-based agent models demonstrate competitive performance, they still exhibit significant deviations from real-world fund companies. A critical distinction lies in the agents' reliance on ``post-reflection'', particularly in response to adverse outcomes, but lack a distinctly human capability: long-term prediction of future trends. Therefore, we introduce QuantAgents, a multi-agent system integrating simulated trading, to comprehensively evaluate various investment strategies and market scenarios without assuming actual risks. Specifically, QuantAgents comprises four agents: a simulated trading analyst, a risk control analyst, a market news analyst, and a manager, who collaborate through several meetings. Moreover, our system incentivizes agents to receive feedback on two fronts: performance in real-world markets and predictive accuracy in simulated trading. Extensive experiments demonstrate that our framework excels across all metrics, yielding an overall return of nearly 300% over the three years (https://quantagents.github.io/).

Problem

• Developing multi-agent financial system with simulated trading
• Addressing limitations in current LLM-based financial agent models
• Evaluating investment strategies without assuming actual risks

Innovation

• Multi-agent system integrating simulated trading for finance
• Four specialized agents collaborating through iterative meetings
• Dual feedback mechanism from real markets and simulations