Abstract
LLMs have demonstrated significant potential in quantitative finance by processing vast unstructured data to emulate human-like analytical workflows. However, current LLM-based methods primarily follow either an Asset-Centric paradigm focused on individual stock prediction or a Market-Centric approach for portfolio allocation, often remaining agnostic to the underlying reasoning that drives market movements. In this paper, we propose a Logic-Oriented perspective, modeling the financial market as a dynamic, evolutionary ecosystem of competing investment narratives, termed Modes of Thought. To operationalize this view, we introduce MEME (Modeling the Evolutionary Modes of Financial Markets), designed to reconstruct market dynamics through the lens of evolving logics. MEME employs a multi-agent extraction module to transform noisy data into high-fidelity Investment Arguments and utilizes Gaussian Mixture Modeling to uncover latent consensus within a semantic space. To model semantic drift among different market conditions, we also implement a temporal evaluation and alignment mechanism to track the lifecycle and historical profitability of these modes. By prioritizing enduring market wisdom over transient anomalies, MEME ensures that portfolio construction is guided by robust reasoning. Extensive experiments on three heterogeneous Chinese stock pools from 2023 to 2025 demonstrate that MEME consistently outperforms seven SOTA baselines. Further ablation studies, sensitivity analysis, lifecycle case study and cost analysis validate MEME's capacity to identify and adapt to the evolving consensus of financial markets. Our implementation can be found at this https URL.
Abstract (translated)
大型语言模型（LLMs）在量化金融领域展示了显著的潜力，通过处理大量非结构化数据来模拟类似人类的分析工作流程。然而，目前基于LLM的方法主要遵循两种范式：一种是专注于个股预测的资产中心主义方法；另一种则是用于投资组合配置的市场中心主义方法，两者通常忽视了推动市场变动的根本原因。在本文中，我们提出了一种逻辑导向视角，将金融市场建模为一个动态、进化的竞争性投资叙事生态系统，称为思想模式（Modes of Thought）。为了实现这一观点，我们引入了MEME（Modeling the Evolutionary Modes of Financial Markets），旨在通过不断演化的逻辑来重建市场动态。MEME采用多代理提取模块将嘈杂的数据转换为高保真的投资论据，并使用高斯混合模型在语义空间内揭示潜在的共识。为了模拟不同市场条件下语义漂移，我们还实施了一种时间评估和对齐机制，以跟踪这些模式的生命历程及其历史盈利能力。通过优先考虑持久的市场智慧而非短暂异常，MEME确保投资组合构建由稳健的理由引导。 从2023年到2025年的三个异质中国股票池中进行的大量实验表明，MEME在七种最先进的基准方法上始终表现出色。进一步的消融研究、敏感性分析、生命周期案例研究和成本分析验证了MEME识别并适应金融市场不断演变共识的能力。 我们的实现可以在以下网址找到：[此处插入实际链接]
URL
https://arxiv.org/abs/2602.11918
