arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.04643cs.AI
收藏

QuantAgents:通过模拟交易构建多智能体金融系统

QuantAgents: Towards Multi-agent Financial System via Simulated Trading

South China University of Technology(南方科技大学);Pazhou Lab(琶洲实验室);Foshan University(佛山大学)

Xiangyu Li, Yawen Zeng, Xiaofen Xing, Jin Xu, Xiangmin Xu

AI总结:

针对现有LLM智能体缺乏长期趋势预测能力的问题,本文提出集成模拟交易的多智能体系统QuantAgents,通过四类智能体协作与双维度反馈机制,在三年实验中取得近300%的总回报率。

摘要:

本文旨在开发一套融合模拟交易的多智能体金融系统,模拟交易是金融从业者广泛使用的技术。当前基于大语言模型(LLM)的智能体模型虽展现出颇具竞争力的性能,但与现实中的基金公司仍存在显著差异。其中一个关键区别在于,现有智能体依赖“事后反思”,尤其是在应对不利结果时,但缺乏人类特有的能力:对未来趋势的长期预测。为此,我们提出QuantAgents——一套集成模拟交易的多智能体系统,可在不承担实际风险的前提下,全面评估各类投资策略与市场场景。具体而言,QuantAgents包含四类智能体:模拟交易分析师、风控分析师、市场新闻分析师与经理,它们通过多轮会议协作。此外,该系统从两个维度激励智能体获取反馈:真实市场中的表现,以及模拟交易中的预测准确率。大量实验表明,我们的框架在所有指标上均表现优异,三年间总回报率接近300%(相关信息见https://quantagents.github.io/)。

英文摘要:

In this paper, our objective is to develop a multi-agent financial system that incorporates simulated trading, a technique extensively utilized by financial professionals. While current LLM-based agent models demonstrate competitive performance, they still exhibit significant deviations from real-world fund companies. A critical distinction lies in the agents' reliance on ``post-reflection'', particularly in response to adverse outcomes, but lack a distinctly human capability: long-term prediction of future trends. Therefore, we introduce QuantAgents, a multi-agent system integrating simulated trading, to comprehensively evaluate various investment strategies and market scenarios without assuming actual risks. Specifically, QuantAgents comprises four agents: a simulated trading analyst, a risk control analyst, a market news analyst, and a manager, who collaborate through several meetings. Moreover, our system incentivizes agents to receive feedback on two fronts: performance in real-world markets and predictive accuracy in simulated trading. Extensive experiments demonstrate that our framework excels across all metrics, yielding an overall return of nearly 300% over the three years (https://quantagents.github.io/).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑