LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
This provides a tractable test bed for policy evaluation at societal scale, potentially helping build better civilizations, though it appears incremental in applying existing methods to a new domain.
The paper tackles the problem of designing and assessing economic policies in strategic environments by introducing the LLM Economist framework, which uses agent-based modeling with large language model-based agents to simulate populations of up to 100 interacting agents, resulting in improved aggregate social welfare relative to Saez solutions.
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.