MEME: Modeling the Evolutionary Modes of Financial Markets

2026-02-12

AI Summary

This work addresses the limitation of existing large language models in capturing the underlying logic driving market dynamics and the evolving nature of investment narratives. Proposing a logic-oriented perspective, it introduces the novel concept of “modes of reasoning” and conceptualizes financial markets as dynamic ecosystems composed of competing investment narratives. The approach integrates multi-agent information extraction, Gaussian mixture modeling of semantic spaces, temporal alignment mechanisms, and argument-based portfolio construction to identify and track persistent market consensus and its evolution. Empirical evaluation across three heterogeneous A-share portfolios from 2023 to 2025 demonstrates significant outperformance over seven state-of-the-art baselines. Ablation studies and case analyses further validate the model’s adaptability to complex market dynamics.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Knowledge Representation and Reasoning: Argumentation
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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 https://github.com/gta0804/MEME.

Problem

• financial markets
• investment narratives
• market dynamics
• evolutionary modes
• reasoning

Innovation

• Logic-Oriented Modeling
• Investment Narratives
• Gaussian Mixture Modeling
• Semantic Drift
• Multi-Agent Argument Extraction