LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra

TL;DR

The paper introduces the LLM Economist framework, leveraging large language models for agent-based economic simulations and mechanism design, enabling credible fiscal policy experimentation with realistic populations and strategic interactions.

Contribution

It presents a novel multi-agent simulation using LLMs for economic policy design, including demographic realism and natural language mechanism specification.

Findings

Planner converges near Stackelberg equilibria improving social welfare.

Demographic realism enhances simulation credibility.

Decentralized voting further improves policy outcomes.

Abstract

We present the LLM Economist, a novel framework that uses agent-based modeling to design and assess economic policies in strategic environments with hierarchical decision-making. At the lower level, bounded rational worker agents -- instantiated as persona-conditioned prompts sampled from U.S. Census-calibrated income and demographic statistics -- choose labor supply to maximize text-based utility functions learned in-context. At the upper level, a planner agent employs in-context reinforcement learning to propose piecewise-linear marginal tax schedules anchored to the current U.S. federal brackets. This construction endows economic simulacra with three capabilities requisite for credible fiscal experimentation: (i) optimization of heterogeneous utilities, (ii) principled generation of large, demographically realistic agent populations, and (iii) mechanism design -- the ultimate nudging problem -- expressed entirely in natural language. Experiments with populations of up to one hundred interacting agents show that the planner converges near Stackelberg equilibria that improve aggregate social welfare relative to Saez solutions, while a periodic, persona-level voting procedure furthers these gains under decentralized governance. These results demonstrate that large language model-based agents can jointly model, simulate, and govern complex economic systems, providing a tractable test bed for policy evaluation at the societal scale to help build better civilizations.