HedgeAgents: A Balanced-aware Multi-agent Financial Trading System

ArXiv ID: 2502.13165 “View on arXiv”

Authors: Unknown

Abstract

As automated trading gains traction in the financial market, algorithmic investment strategies are increasingly prominent. While Large Language Models (LLMs) and Agent-based models exhibit promising potential in real-time market analysis and trading decisions, they still experience a significant -20% loss when confronted with rapid declines or frequent fluctuations, impeding their practical application. Hence, there is an imperative to explore a more robust and resilient framework. This paper introduces an innovative multi-agent system, HedgeAgents, aimed at bolstering system robustness via ``hedging’’ strategies. In this well-balanced system, an array of hedging agents has been tailored, where HedgeAgents consist of a central fund manager and multiple hedging experts specializing in various financial asset classes. These agents leverage LLMs’ cognitive capabilities to make decisions and coordinate through three types of conferences. Benefiting from the powerful understanding of LLMs, our HedgeAgents attained a 70% annualized return and a 400% total return over a period of 3 years. Moreover, we have observed with delight that HedgeAgents can even formulate investment experience comparable to those of human experts (https://hedgeagents.github.io/).

Keywords: multi-agent system, hedging strategies, Large Language Models (LLMs), financial asset classes, Financial Markets

Complexity vs Empirical Score

• Math Complexity: 2.0/10
• Empirical Rigor: 7.5/10
• Quadrant: Street Traders
• Why: The paper relies primarily on LLM agent architecture and system design rather than advanced mathematical modeling, but presents extensive empirical results with specific performance metrics (70% annualized return, 400% total return over 3 years), backtest comparisons against multiple baselines, and a live demo link.

  flowchart TD
    A["Research Goal: How to enhance LLM-based trading<br>robustness against market declines?"] --> B["Methodology: HedgeAgents Multi-Agent System<br>Central Manager + Hedging Experts"]
    B --> C["Inputs: Market Data &<br>Financial Asset Class Information"]
    C --> D["Computation: LLM Cognitive Reasoning &<br>Three Types of Agent Conferences"]
    D --> E["Process: Hedging Strategy Execution<br>& Real-time Coordination"]
    E --> F["Outcome: 70% Annualized Return<br>400% Total Return over 3 Years"]
    F --> G["Outcome: Formulated Investment Experience<br>Comparable to Human Experts"]