Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TradingAgents: Multi-Agents LLM Financial Trading Framework

Yijia Xiao, Edward Sun, Di Luo, Wei Wang

TL;DR

<3-5 sentence high-level summary>

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.

TradingAgents: Multi-Agents LLM Financial Trading Framework

TL;DR

<3-5 sentence high-level summary>

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.
Paper Structure (34 sections, 4 equations, 11 figures, 1 table)

This paper contains 34 sections, 4 equations, 11 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. LLMs as Financial Assistants
  4. LLMs as Traders
  5. LLMs as Alpha Miners
  6. TradingAgents: Role Specialization
  7. Analyst Team
  8. Researcher Team
  9. Trader Agents
  10. Risk Management Team
  11. TradingAgents: Agent Workflow
  12. Communication Protocol
  13. Types of Agent Interactions
  14. Backbone LLMs
  15. Experiments
  16. ...and 19 more sections

Figures (11)

  • Figure 1: TradingAgents Overall Framework Organization. I. Analysts Team: Four analysts concurrently gather relevant market information. II. Research Team: The team discusses and evaluates the collected data. III. Trader: Based on the researchers' analysis, the trader makes the trading decision. IV. Risk Management Team: Risk guardians assess the decision against current market conditions to mitigate risks. V. Fund Manager: The fund manager approves and executes the trade.
  • Figure 2: TradingAgents Analyst Team
  • Figure 3: TradingAgents Researcher Team: Bullish Perspectives and Bearish Perspectives
  • Figure 4: TradingAgents's Trader Decision-Making Process
  • Figure 5: TradingAgents Risk Management Team and Fund Manager Approval Workflow
  • ...and 6 more figures