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

TL;DR

MiniFed is a novel framework that uses large language model agents to simulate FOMC meetings, enabling accurate Federal Funds rate projections and providing a new approach to understanding decision-making processes in monetary policy.

Contribution

This paper introduces MiniFed, the first framework employing LLM agents to simulate FOMC meetings and optimize monetary policy decision-making processes.

Findings

Achieves high accuracy in Federal Funds rate projections

Behaviorally aligns with real-world FOMC members

Serves as a benchmark for future LLM-based conference simulations

Abstract

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.