arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.04788cs.AIcs.CLcs.LGq-fin.STq-fin.TR
收藏

增强投资分析:优化金融研究中的AI智能体协作

Enhancing Investment Analysis: Optimizing AI-Agent Collaboration in Financial Research

Tsinghua University(清华大学);AI4Finance Foundation(AI4金融基金会);University of Maryland, College Park(马里兰大学学院公园分校)

Xuewen Han, Neng Wang, Shangkun Che, Hongyang Yang, Kunpeng Zhang, Sean Xin Xu

AI总结:

本文提出一种多智能体协作系统,通过可配置的智能体组和次优组合策略,在金融研究中优于单智能体模型,提升准确性、效率和适应性。

摘要:

近年来,生成式人工智能(GenAI)在金融分析和投资决策中的应用受到了广泛关注。然而,现有的大多数方法依赖于单智能体系统,未能充分利用多个AI智能体的协作潜力。在本文中,我们提出了一种新颖的多智能体协作系统,旨在增强金融投资研究中的决策能力。该系统包含具有可配置组大小和协作结构的智能体组,以利用每种智能体组类型的优势。通过采用次优组合策略,系统能够动态适应不同的市场条件和投资场景,优化不同任务下的性能。我们聚焦于三个子任务:基本面分析、市场情绪和风险分析,通过分析道琼斯指数中30家公司2023年的SEC 10-K表格。我们的研究结果揭示了不同任务下AI智能体配置所带来的显著性能差异。结果表明,我们的多智能体协作系统优于传统的单智能体模型,在复杂的金融环境中提供了更高的准确性、效率和适应性。本研究强调了多智能体系统通过整合多样化的分析视角,在变革金融分析和投资决策方面的潜力。

英文摘要:

In recent years, the application of generative artificial intelligence (GenAI) in financial analysis and investment decision-making has gained significant attention. However, most existing approaches rely on single-agent systems, which fail to fully utilize the collaborative potential of multiple AI agents. In this paper, we propose a novel multi-agent collaboration system designed to enhance decision-making in financial investment research. The system incorporates agent groups with both configurable group sizes and collaboration structures to leverage the strengths of each agent group type. By utilizing a sub-optimal combination strategy, the system dynamically adapts to varying market conditions and investment scenarios, optimizing performance across different tasks. We focus on three sub-tasks: fundamentals, market sentiment, and risk analysis, by analyzing the 2023 SEC 10-K forms of 30 companies listed on the Dow Jones Index. Our findings reveal significant performance variations based on the configurations of AI agents for different tasks. The results demonstrate that our multi-agent collaboration system outperforms traditional single-agent models, offering improved accuracy, efficiency, and adaptability in complex financial environments. This study highlights the potential of multi-agent systems in transforming financial analysis and investment decision-making by integrating diverse analytical perspectives.

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。

↑