QuantAgent：基於價格驅動的多智能體大語言模型實現高頻交易

QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

September 12, 2025

作者: Fei Xiong, Xiang Zhang, Aosong Feng, Siqi Sun, Chenyu You

cs.AI

摘要

近期，大型語言模型（LLMs）在金融推理與市場理解方面展現了令人矚目的能力。如TradingAgent和FINMEM等多代理LLM框架，通過利用基本面與情緒導向的輸入，增強了這些模型在長期投資任務中的表現。然而，此類系統並不適合高頻交易（HFT）對高速與精確性的嚴苛要求。HFT需要基於結構化、短期信號（包括技術指標、圖表形態及趨勢特徵）做出快速且風險意識的決策，這與傳統金融LLM應用中典型的長期語義推理截然不同。為此，我們推出了QuantAgent，這是首個專為高頻算法交易設計的多代理LLM框架。該系統將交易分解為四個專業代理：指標、形態、趨勢與風險，每個代理均配備了領域專用工具與結構化推理能力，以捕捉短期時間窗口內市場動態的不同面向。在涵蓋比特幣與納斯達克期貨等十種金融工具的零樣本評估中，QuantAgent在4小時交易區間內的預測準確度與累計收益上均展現出優異表現，超越了強大的神經網絡與基於規則的基準模型。我們的研究表明，將結構化金融先驗知識與語言本質推理相結合，為高頻金融市場中可追溯的實時決策系統開闢了新的潛力。

English

Recent advances in Large Language Models (LLMs) have demonstrated impressive capabilities in financial reasoning and market understanding. Multi-agent LLM frameworks such as TradingAgent and FINMEM augment these models to long-horizon investment tasks, leveraging fundamental and sentiment-based inputs for strategic decision-making. However, such systems are ill-suited for the high-speed, precision-critical demands of High-Frequency Trading (HFT). HFT requires rapid, risk-aware decisions based on structured, short-horizon signals, including technical indicators, chart patterns, and trend-based features, distinct from the long-term semantic reasoning typical of traditional financial LLM applications. To this end, we introduce QuantAgent, the first multi-agent LLM framework explicitly designed for high-frequency algorithmic trading. The system decomposes trading into four specialized agents, Indicator, Pattern, Trend, and Risk, each equipped with domain-specific tools and structured reasoning capabilities to capture distinct aspects of market dynamics over short temporal windows. In zero-shot evaluations across ten financial instruments, including Bitcoin and Nasdaq futures, QuantAgent demonstrates superior performance in both predictive accuracy and cumulative return over 4-hour trading intervals, outperforming strong neural and rule-based baselines. Our findings suggest that combining structured financial priors with language-native reasoning unlocks new potential for traceable, real-time decision systems in high-frequency financial markets.