The Analyst Team (Figure 2) is composed of specialized agents responsible for gathering and analyzing various types of market data to inform trading decisions. Each agent focuses on a specific aspect of market analysis, bringing together a comprehensive view of the market's conditions.
+The Analyst Team is composed of specialized agents responsible for gathering and analyzing various types of market data to inform trading decisions. Each agent focuses on a specific aspect of market analysis, bringing together a comprehensive view of the market's conditions.
-
-
+ 
+ 
+ 
+ - Fundamental Analyst Agents: These agents evaluate company fundamentals by analyzing financial statements, earnings reports, insider transactions, and other pertinent data. They assess a company's intrinsic value to identify undervalued or overvalued stocks, providing insights into long-term investment potential. @@ -207,12 +229,7 @@
- Bullish Researchers: These agents advocate for investment opportunities by highlighting positive indicators, growth potential, and favorable market conditions. They construct arguments supporting the initiation or continuation of positions in certain assets. @@ -224,14 +241,7 @@
- Evaluating recommendations and insights from analysts and researchers. @@ -245,14 +255,7 @@
- Assessing factors such as market volatility, liquidity, and counterparty risks. @@ -363,107 +366,82 @@
Researcher Team
The Researcher Team (Figure 3) is responsible for critically evaluating the information provided by the Analyst Team. Comprised of agents adopting both bullish and bearish perspectives, they engage in multiple rounds of debate to assess the potential risks and benefits of investment decisions.
- -
- The Researcher Team is responsible for critically evaluating the information provided by the Analyst Team. Comprised of agents adopting both bullish and bearish perspectives, they engage in multiple rounds of debate to assess the potential risks and benefits of investment decisions.
Trader Agents
Trader Agents (Figure 4) are responsible for executing trading decisions based on the comprehensive analysis provided by the Analyst Team and the nuanced perspectives from the Researcher Team. They assess the synthesized information, considering both quantitative data and qualitative insights, to determine optimal trading actions.
- -
- The tasks of TradingAgents Trader include:
+Trader Agents are responsible for executing trading decisions based on the comprehensive analysis provided by the Analyst Team and the nuanced perspectives from the Researcher Team. They assess the synthesized information, considering both quantitative data and qualitative insights, to determine optimal trading actions.
Risk Management Team
The Risk Management Team (Figure 5) monitors and controls the firm's exposure to various market risks. These agents continuously evaluate the portfolio's risk profile, ensuring that trading activities remain within predefined risk parameters and comply with regulatory requirements.
- -
- The responsibilities of Risk Management Team include:
+The Risk Management Team monitors and controls the firm's exposure to various market risks. These agents continuously evaluate the portfolio's risk profile, ensuring that trading activities remain within predefined risk parameters and comply with regulatory requirements.
| Categories | -Models | -AAPL | -- | GOOGL | -- | AMZN | -||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| - | - | CR%↑ | -ARR%↑ | -SR↑ | -MDD%↓ | -- | CR%↑ | -ARR%↑ | -SR↑ | -MDD%↓ | -- | CR%↑ | -ARR%↑ | -SR↑ | -MDD%↓ | +Metric | +Buy and Hold | +MACD | +KDJ & RSI | +ZMR | +SMA | +TradingAgents |
| Market | -B&H | --5.23 | -5.09 | -1.29 | 11.90 | -- | 7.78 | 8.09 | 1.35 | 13.04 | -- | 17.1 | 17.6 | 3.53 | 3.80 | +Cumulative Return (CR%) | +-5.23 | +-1.49 | +2.05 | +0.57 | +-3.2 | +26.62 |
| Rule-based | -MACD | --1.49 | -1.48 | -0.81 | 4.53 | -- | 6.20 | 6.26 | 2.31 | 1.22 | -- | - | - | - | - | +Annualized Return (AR%) | +-5.09 | +-1.48 | +2.07 | +0.57 | +-2.97 | +30.50 |
| KDJ&RSI | -2.05 | 2.07 | 1.64 | 1.09 | -- | 0.4 | 0.4 | 0.02 | 1.58 | -- | -0.77 | -0.76 | -2.25 | 1.08 | +Sharpe Ratio (SR) | +-1.29 | +-0.81 | +1.64 | +0.17 | +-1.72 | +8.21 | |
| ZMR | -0.57 | 0.57 | 0.17 | 0.86 | -- | -0.58 | 0.58 | 2.12 | 2.34 | -- | -0.77 | -0.77 | -2.45 | 0.82 | -||||||||
| SMA | --3.2 | -2.97 | -1.72 | 3.67 | -- | 6.23 | 6.43 | 2.12 | 2.34 | -- | 11.01 | 11.6 | 2.22 | 3.97 | -||||||||
| Ours | -TradingAgents | -26.62 | 30.5 | 8.21 | 0.91 | -- | 24.36 | 27.58 | 6.39 | 1.69 | -- | 23.21 | 24.90 | 5.60 | 2.11 | -|||||||
| Improvement(%) | -24.57 | 28.43 | 6.57 | - | -- | 16.58 | 19.49 | 4.26 | - | -- | 6.10 | 7.30 | 2.07 | - | +Maximum Drawdown (MDD%) | +11.90 | +4.53 | +1.09 | +0.86 | +3.67 | +0.91 | |
Table 1: TradingAgents (AIS): Comparison of RNA Sequence (left), Modality Fusion (middle), and TradingAgents (right). Embedding base models are BERT, PubMedBERT, and OpenAI's GPT text-embedding-3-large.
+Table 1: Performance comparison of TradingAgents against baseline models using four evaluation metrics.
-Sharpe Ratio
-The Sharpe Ratio performance highlights TradingAgents' exceptional ability to deliver superior risk-adjusted returns, consistently outperforming all baseline models across AAPL, GOOGL, and AMZN with Sharpe Ratios of at least 5.60—surpassing the next best models by a significant margin of at least 2.07 points. This result underscores TradingAgents' effectiveness in balancing returns against risk, a critical metric for sustainable and predictable investment growth. By excelling over market benchmarks like Buy-and-Hold and advanced strategies such as KDJRSI, SMA, MACD, and ZMR, TradingAgents demonstrates its adaptability and robustness in diverse market conditions. Its ability to maximize returns while maintaining controlled risk exposure establishes a solid foundation for multi-agent and debate-based automated trading algorithms.
+Cumulative Return (CR)
+The cumulative return measures the total return generated over the simulation period. It is calculated as:
++ CR = ((Vend - Vstart) / Vstart) × 100% +
+where Vend is the portfolio value at the end of the simulation, and Vstart is the initial portfolio value.
-Maximum Drawdown
-While rule-based baselines demonstrated superior performance in controlling risk, as reflected by their maximum drawdown scores, they fell short in capturing high returns. This trade-off between risk and reward underscores TradingAgents' strength as a balanced approach. Despite higher returns being typically associated with higher risks, TradingAgents maintained a relatively low maximum drawdown compared to many baselines. Its effective risk-control mechanisms, facilitated by the debates among risk-control agents, ensured that the maximum drawdown remained within a manageable limit, not exceeding 2%. This demonstrates TradingAgents' capability to strike a robust balance between maximizing returns and managing risk effectively.
+Annualized Return (AR)
+The annualized return normalizes the cumulative return over the number of years:
++ AR = (((Vend / Vstart)^(1/N)) - 1) × 100% +
+where N is the number of years in the simulation.
-Explainability
-A significant drawback of current deep learning methods for trading is their dense and complex architectures, which often render the decisions made by trading agents indecipherable to humans. This challenge, rooted in the broader issue of AI explainability, is particularly critical for trading agents, as they operate in real-world financial markets, often involving substantial sums of money where incorrect decisions can lead to severe consequences and losses.
+Sharpe Ratio (SR)
+The Sharpe ratio measures risk-adjusted return by comparing a portfolio's excess return over the risk-free rate to its volatility:
++ SR = (R̄ - Rf) / σ +
+where R̄ is the average portfolio return, Rf is the risk-free rate (e.g., yield of 3-month Treasury bills), and σ is the standard deviation of the portfolio returns.
-In contrast, an LLM-based agentic framework for trading offers a transformative advantage: its operations and decisions are communicated in natural language, making them highly interpretable to humans. To illustrate this, we provide the full trading log of TradingAgents for a single day in the Appendix, showcasing its use of the ReAct-style prompting framework. Each decision made by the agents is accompanied by detailed reasoning, tool usage, and thought processes, enabling traders to easily understand and debug the system. This transparency empowers traders to fine-tune and adjust the framework to account for factors influencing decisions, offering a significant edge in explainability over traditional deep-learning trading algorithms.
+Maximum Drawdown (MDD)
+Maximum drawdown measures the largest peak-to-trough decline in the portfolio value:
++ MDD = maxt ∈ [0, T] ((Peakt - Trought) / Peakt) × 100% +