TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis

TL;DR

TradingGroup is a multi-agent trading system that leverages self-reflection and data-synthesis to improve decision-making and coordination in stock trading, demonstrating superior performance in backtesting experiments.

Contribution

It introduces a novel self-reflective multi-agent architecture with an automated data-synthesis pipeline for enhanced trading performance.

Findings

Outperforms rule-based and machine learning strategies in backtests

Utilizes self-reflection for agents to learn from past successes and failures

Employs data-synthesis to generate high-quality training data

Abstract

Recent advancements in large language models (LLMs) have enabled powerful agent-based applications in finance, particularly for sentiment analysis, financial report comprehension, and stock forecasting. However, existing systems often lack inter-agent coordination, structured self-reflection, and access to high-quality, domain-specific post-training data such as data from trading activities including both market conditions and agent decisions. These data are crucial for agents to understand the market dynamics, improve the quality of decision-making and promote effective coordination. We introduce TradingGroup, a multi-agent trading system designed to address these limitations through a self-reflective architecture and an end-to-end data-synthesis pipeline. TradingGroup consists of specialized agents for news sentiment analysis, financial report interpretation, stock trend forecasting, trading style adaptation, and a trading decision making agent that merges all signals and style preferences to produce buy, sell or hold decisions. Specifically, we design self-reflection mechanisms for the stock forecasting, style, and decision-making agents to distill past successes and failures for similar reasoning in analogous future scenarios and a dynamic risk-management model to offer configurable dynamic stop-loss and take-profit mechanisms. In addition, TradingGroup embeds an automated data-synthesis and annotation pipeline that generates high-quality post-training data for further improving the agent performance through post-training. Our backtesting experiments across five real-world stock datasets demonstrate TradingGroup's superior performance over rule-based, machine learning, reinforcement learning, and existing LLM-based trading strategies.