FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction

TL;DR

FedSight AI reframes FOMC rate prediction as emergent collective reasoning among specialized LLM-based agents, integrating both structured economic indicators and unstructured narratives (Beige Book, Dot Plot, FedWatch). The authors introduce a Chain-of-Draft mechanism to enforce concise, multi-stage reasoning, and demonstrate that a clustering-based set of representative agents can capture heterogeneity while remaining tractable. In backtests on 2023–2024 meetings, FedSight CoD achieves high directional and total accuracy with strong stability and reduced token usage, outperforming MiniFed and Ordinal RF baselines. The work offers a transparent, policy-aligned forecasting paradigm that links deliberation to interpretable outputs, with implications for policymakers and markets alike.

Abstract

The Federal Open Market Committee (FOMC) sets the federal funds rate, shaping monetary policy and the broader economy. We introduce \emph{FedSight AI}, a multi-agent framework that uses large language models (LLMs) to simulate FOMC deliberations and predict policy outcomes. Member agents analyze structured indicators and unstructured inputs such as the Beige Book, debate options, and vote, replicating committee reasoning. A Chain-of-Draft (CoD) extension further improves efficiency and accuracy by enforcing concise multistage reasoning. Evaluated at 2023-2024 meetings, FedSight CoD achieved accuracy of 93.75\% and stability of 93.33\%, outperforming baselines including MiniFed and Ordinal Random Forest (RF), while offering transparent reasoning aligned with real FOMC communications.

Figures (1)

• Figure 1: Workflow of FedSight AI multi-agent system for FOMC prediction.