Agent-Based Simulation of a Financial Market with Large Language Models

2025-10-14

AI Summary

Empirical stock markets exhibit path-dependent price anomalies—such as abnormal declines following proximity to historical highs—that defy fundamental explanations and reflect investors’ reliance on dynamic psychological reference points (e.g., purchase price, prior peaks), a behavior poorly captured by conventional agent-based models. Method: We propose FCLAgent—the first trading agent integrating a large language model (LLM) with a rule-based execution module. The LLM models individual loss aversion and adaptively updates reference points in response to evolving market conditions; the rule module determines order price and size. Contribution/Results: Experiments demonstrate that FCLAgent successfully reproduces path-dependent price patterns unattainable with traditional agents. Behavioral analysis confirms the endogenous, time-varying nature of reference points. This work pioneers the use of LLMs in micro-level financial behavioral modeling, uncovering the cognitive mechanisms underpinning path dependence.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Game Theory and Economic Paradigms: Behavioral Game Theory

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

In real-world stock markets, certain chart patterns -- such as price declines near historical highs -- cannot be fully explained by fundamentals alone. These phenomena suggest the presence of path dependence in price formation, where investor decisions are influenced not only by current market conditions but also by the trajectory of prices leading up to the present. Path dependence has drawn attention in behavioral finance as a key mechanism behind such anomalies. One plausible driver of path dependence is human loss aversion, anchored to individual reference points like purchase prices or past peaks, which vary with personal context. However, capturing such subtle behavioral tendencies in traditional agent-based market simulations has remained a challenge. We propose the Fundamental-Chartist-LLM-Agent (FCLAgent), which uses large language models (LLMs) to emulate human-like trading decisions. In this framework, (1) buy/sell decisions are made by LLMs based on individual situations, while (2) order price and volume follow standard rule-based methods. Simulations show that FCLAgents reproduce path-dependent patterns that conventional agents fail to capture. Furthermore, an analysis of FCLAgents' behavior reveals that the reference points guiding loss aversion vary with market trajectories, highlighting the potential of LLM-based agents to model nuanced investor behavior.

Problem

• Modeling path dependence in financial markets using LLM agents
• Capturing investor loss aversion with individual reference points
• Reproducing unexplained chart patterns through behavioral simulation

Innovation

• LLM-based agents make human-like trading decisions
• Order price and volume use rule-based methods
• Agents capture path dependence with varying reference points