TradingAgents: Multi-Agents LLM Financial Trading Framework

TL;DR

TradingAgents introduces a multi-agent LLM-based framework that simulates collaborative trading environments, improving financial trading performance through specialized roles and dynamic interactions among agents.

Contribution

The paper presents a novel multi-agent LLM framework for financial trading that models real-world trading firm dynamics, enhancing decision-making and performance.

Findings

Outperforms baseline models in cumulative returns

Achieves higher Sharpe ratio

Reduces maximum drawdown

Abstract

Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs). In finance, efforts have largely focused on single-agent systems handling specific tasks or multi-agent frameworks independently gathering data. However, the multi-agent systems' potential to replicate real-world trading firms' collaborative dynamics remains underexplored. TradingAgents proposes a novel stock trading framework inspired by trading firms, featuring LLM-powered agents in specialized roles such as fundamental analysts, sentiment analysts, technical analysts, and traders with varied risk profiles. The framework includes Bull and Bear researcher agents assessing market conditions, a risk management team monitoring exposure, and traders synthesizing insights from debates and historical data to make informed decisions. By simulating a dynamic, collaborative trading environment, this framework aims to improve trading performance. Detailed architecture and extensive experiments reveal its superiority over baseline models, with notable improvements in cumulative returns, Sharpe ratio, and maximum drawdown, highlighting the potential of multi-agent LLM frameworks in financial trading. TradingAgents is available at https://github.com/TauricResearch/TradingAgents.