Fidelity Breeds Complexity: Simulating Stock Markets with Large-Scale Generative Agents

ICLR 2026 Conference Submission17297 Authors

Keywords: Large language model agents, Stock market simulation, Social simulation, Agent-based modeling

TL;DR: We introduce MarketSim, the first high-fidelity stock market simulator with large-scale LLM agents trading in a realistic high-frequency NASDAQ-like environment, validated by a comprehensive benchmark.

Abstract: Stock markets are one of the most complex systems in the modern world, where prices emerge from billions of decentralized interactions among heterogeneous participants in an ever-evolving information landscape. Building a high-fidelity stock market simulator is not only a cornerstone for understanding such complexity, but also offers a valuable testbed for anticipating and mitigating crises and disruptions. Despite decades of efforts, existing methods remain confined to an unresolved dilemma: structural fidelity often comes at the cost of non-intelligent agents, while large language model (LLM) agents can only participate in oversimplified market environments. To this end, we propose MarketSim, a large-scale stock market simulation framework with generative agents. Specifically, we first design a hierarchical multi-agent architecture. By decoupling agents’ strategic reasoning from their high-frequency actions, this architecture enables LLM agents to participate in a nanosecond-resolution, NASDAQ-like continuous double auction market. Building on this, we simulate over 15k diverse market participant agents, whose billions of interactions collectively create an evolving market environment in which agents learn from feedback and adapt their strategies accordingly. Furthermore, we ground these agents in a rich informational landscape that covers over 12k real-world news articles, policy documents, and earnings reports. To evaluate our proposed MarketSim, we develop a comprehensive benchmark that includes stocks from 8 GICS sectors and 3 representative real-world scenarios, along with 5 stylized facts for market complexity and 5 price-related statistical metrics. Extensive experiments demonstrate that MarketSim not only captures the complexity characterizing real-world markets, but also accurately tracks real-world high-frequency price dynamics with an average MAPE of 3.48\%. Overall, MarketSim not only offers direct applications in understanding and anticipating financial crises, but also provides evidence for a key tenet of complexity science: fidelity breeds complexity.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 17297