AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments

TL;DR

AgentEconomist is an interactive system that transforms economic intuitions into executable experiments by leveraging a large knowledge base and human-AI collaboration, improving research idea quality.

Contribution

It introduces a modular, multi-stage architecture for translating economic insights into experiments, integrating human input and large language models.

Findings

System generates more literature-grounded research ideas.

Achieves higher novelty and insight than generic LLMs.

Validated through expert evaluation and large language models.

Abstract

A long-standing challenge in economics lies not in the lack of intuition, but in the difficulty of translating intuitive insights into verifiable research. To address this challenge, we introduce AgentEconomist, an end-to-end interactive system designed to translate abstract intuitions into executable computational experiments. Grounded in a domain-specific knowledge base covering over 13,000 high-quality academic papers, the system employs a modular multi-stage architecture. Specifically, the Idea Development Stage generates literature-grounded hypotheses, the Experimental Design Stage configures simulator-aligned experimental parameters and protocols, and the Experimental Execution Stage runs experiments and returns structured analyses. Together, these stages form a human-in-the-loop, iterative workflow that translates economic intuitions into executable computational experiments. Through extensive experiments involving human expert evaluation and large language models (LLMs) as judges, we show that the system generates research ideas with stronger literature grounding and higher novelty and insight than state-of-the-art generic LLMs. Overall, AgentEconomist adopts a human-AI collaboration paradigm that enables researchers to focus on high-level intuitions, while delegating the labor-intensive processes of translation and computational execution to agents.