TradingAgents: Multi-Agents LLM Financial Trading Framework
TradingAgents proposes a multi-agent LLM framework with specialized trading roles and collaborative dynamics, outperforming baselines on cumulative returns, Sharpe ratio, and drawdown.
Published Dec 28, 20246 citations▲ 150 on Hugging FaceCode ★ 110,044arXiv ↗
Only vote on papers you've read. Sign in with GitHub to vote.
TradingAgents earns praise for genuinely simulating collaborative trading-firm dynamics with Bull/Bear debates and risk guardrails, but its backtest-only results without transaction costs, live market impact, or a single-agent baseline leave its real-world edge unproven.
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.