Simulating FOMC Meetings with LLM-Based Agents

Summary

MiniFed is a framework for simulating Federal Open Market Committee meetings with large language model agents. It aims to represent meeting members and the committee’s decision process, shifting attention from studying only the effects of Federal Funds rate changes to modeling how rate decisions are reached. The framework is organized as a five-stage workflow and includes an effort to optimize the simulated committee structure.

The paper reports experiments in which the framework projects Federal Funds rates with high accuracy and produces agent behavior aligned with real-world counterparts. The description provides no details about datasets, evaluation metrics, forecast horizons, or comparison baselines, so the strength and generality of those results cannot be assessed here. The work concerns policy-decision simulation and rate projection; it does not specify a direct trading strategy or demonstrate market returns.

Key ideas

• MiniFed uses LLM agents to model members and processes in FOMC meetings.
• Its five-stage workflow aims to simulate committee deliberation and optimize committee structure.
• The framework targets Federal Funds rate projections as well as meeting-process reconstruction.
• Reported experiments claim accurate projections and behavioral alignment, but the available description omits evaluation details.
• The paper focuses on policy simulation rather than a specific market trading strategy.

Tags

# MiniFed : Integrating LLM-based Agentic-Workflow for Simulating FOMC Meeting


# MiniFed : Integrating LLM-based Agentic-Workflow for Simulating FOMC Meeting









The Federal Funds rate in the United States plays a significant role in both domestic and international financial markets. However, research has predominantly focused on the effects of adjustments to the Federal Funds rate rather than on the decision-making process itself. Recent advancements in large language models(LLMs) offer a potential method for reconstructing the original FOMC meetings, which are responsible for setting the Federal Funds rate. In this paper, we propose a five-stage FOMC meeting simulation framework, MiniFed, which employs LLM agents to simulate real-world FOMC meeting members and optimize the FOMC structure. This framework effectively revitalizes the FOMC meeting process and facilitates projections of the Federal Funds rate. Experimental results demonstrate that our proposed MiniFed framework achieves both high accuracy in Federal Funds rate projections and behavioral alignment with the agents' real-world counterparts. Given that few studies have focused on employing LLM agents to simulate large-scale real-world conferences, our work can serve as a benchmark for future developments.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.