Gate Research: Multi-Agent LLM Trading Framework Significantly Outperforms Buy & Hold Strategy in BTC Backtesting
Odaily News, Gate Research recently released a report titled "Research and Backtesting Analysis of a Multi-Agent LLM-Based BTC Trading Framework," which points out that compared to a single LLM directly generating trading signals, the Multi-Agent LLM architecture more closely mimics the research and investment workflow of real financial institutions. By enabling collaboration and debate among analysts, researchers, traders, and risk control teams, it enhances the transparency and risk control capabilities of trading decisions. The research utilized the TradingAgents framework to construct an AI trading system suitable for the crypto market context, incorporating multiple agent roles such as technical analysis, news analysis, sentiment analysis, and macro/on-chain analysis.
Based on BTC/USDT 1-hour interval data, the study conducted a historical backtest of the TradingAgents-BTC strategy. The results show that the strategy achieved a total return of +20.25% during the test period, significantly outperforming the Buy & Hold strategy's -7.89% over the same period. Additionally, the maximum drawdown was controlled at -17.41%, lower than the -27.06% recorded by Buy & Hold. The research suggests that during consolidation and downtrend phases, the multi-agent framework can reduce risk exposure through Sell/Underweight and Flat states, and re-establish long positions during market rebounds, thereby improving overall risk-adjusted returns.
The report notes that the Multi-Agent LLM framework demonstrates certain application potential in crypto trading scenarios. However, the current backtesting period covers only approximately three months, and 1-hour interval trading may still be affected by transaction fees, slippage, and signal latency. Future efforts will need to further validate the strategy's stability and generalization capabilities over longer historical periods, across different market conditions, and with a broader range of asset classes.
