AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models

2026-06-18

AI Summary

This study addresses the lack of theoretical grounding and empirical support in large language model (LLM)-based economic analysis by proposing a multi-agent AI economist system that integrates knowledge graphs, formal economic models, and LLMs. Built upon a retrieval-augmented generation (RAG) framework and agent collaboration architecture, the system orchestrates analytical workflows by planning tasks, retrieving authoritative evidence, invoking appropriate economic models, and generating structured reports. This approach yields economic scenario analyses that combine narrative fluency with theoretical and empirical consistency. In case studies examining U.S. inflation persistence, Federal Reserve policy responses, and commercial real estate refinancing risks, the system produces reports with superior logical rigor and traceable conclusions, marking the first successful integration of knowledge graphs, structured economic models, and LLM-based agents in a unified analytical framework.

Abstract

We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs. While LLMs can generate fluent economic narratives, economists are often required to make economic claims grounded by economic theory and real-world data. Based on this motivation, this study proposes an RAG-based AI economist, which utilizes knowledge graphs including economic data and theory and LLM-based agents to plan the analysis, retrieve relevant evidence, select appropriate models, and generate reports. In our framework, we do not produce quantitative claims directly with the language model alone; instead, we generate narratives grounded in explicit model-based computations and linked to the retrieved evidence via AI agents. We refer to our framework as an AI economist agent. We evaluate the AI economist agent in two applications: economist report generation for U.S. inflation persistence and Federal Reserve policy, and bank stress-test narrative generation for U.S. commercial real estate refinancing stress. The results illustrate how grounding the generated reports improves their economic coherence and traceability.

Problem

• economic analysis
• large language models
• retrieval-augmented generation
• knowledge graphs
• model grounding

Innovation

• AI Economist Agent
• Retrieval-Augmented Generation (RAG)
• Knowledge Graphs
• Large Language Models
• Model-Grounded Reasoning