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

arXiv: https://arxiv.org/abs/2507.15815 · HTML: https://mlsanity.com/paper/2507.15815/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 44 of its 77 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 30 of 44)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/1702.03037/) (2017)
- [In-context Reinforcement Learning with Algorithm Distillation](https://mlsanity.com/paper/2210.14215/) (2022)
- [EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities](https://mlsanity.com/paper/2310.10436/) (2023)
- [BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games](https://mlsanity.com/paper/2411.13543/) (2024)
- [OASIS: Open Agent Social Interaction Simulations with One Million Agents](https://mlsanity.com/paper/2411.11581/) (2024)
- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [Motif: Intrinsic Motivation from Artificial Intelligence Feedback](https://mlsanity.com/paper/2310.00166/) (2023)
- [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models](https://mlsanity.com/paper/2404.01230/) (2024)
- [Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach](https://mlsanity.com/paper/2312.11865/) (2023)
- [The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies](https://mlsanity.com/paper/2004.13332/) (2020)
- [LASER: LLM Agent with State-Space Exploration for Web Navigation](https://mlsanity.com/paper/2309.08172/) (2023)
- [Do LLM Agents Exhibit Social Behavior?](https://mlsanity.com/paper/2312.15198/) (2023)
- [Project Sid: Many-agent simulations toward AI civilization](https://mlsanity.com/paper/2411.00114/) (2024)
- [LLM Voting: Human Choices and AI Collective Decision Making](https://mlsanity.com/paper/2402.01766/) (2024)
- [A Survey of In-Context Reinforcement Learning](https://mlsanity.com/paper/2502.07978/) (2025)
- [Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games](https://mlsanity.com/paper/2102.11494/) (2021)
- [Reward Is Enough: LLMs Are In-Context Reinforcement Learners](https://mlsanity.com/paper/2506.06303/) (2025)

## Built on by (most cited first, 23 of 23)

- [Continual Harness: Online Adaptation for Self-Improving Foundation Agents](https://mlsanity.com/paper/2605.09998/) (2026)
- [Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets](https://mlsanity.com/paper/2510.25779/) (2025)
- [FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems](https://mlsanity.com/paper/2605.11514/) (2026)
- [CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models](https://mlsanity.com/paper/2512.07890/) (2025)
- [How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?](https://mlsanity.com/paper/2602.18464/) (2026)
- [Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces](https://mlsanity.com/paper/2605.17698/) (2026)
- [Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems](https://mlsanity.com/paper/2606.04306/) (2026)
- [Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information](https://mlsanity.com/paper/2608.23867/) (2026)
- [What Makes LLM Agent Simulations Useful for Policy Practice? An Iterative Design Study in Emergency Preparedness](https://mlsanity.com/paper/2509.21868/) (2025)
- [Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Data](https://mlsanity.com/paper/2511.14098/) (2025)
- [The Emergence of Social Science of Large Language Models](https://mlsanity.com/paper/2509.24877/) (2025)
- [MARO: Learning Stronger Reasoning from Social Interaction](https://mlsanity.com/paper/2601.12323/) (2026)
- [Evaluation of Agents under Simulated AI Marketplace Dynamics](https://mlsanity.com/paper/2604.14256/) (2026)
- [Soft-Label Governance for Distributional Safety in Multi-Agent Systems](https://mlsanity.com/paper/2604.19752/) (2026)
- [Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis](https://mlsanity.com/paper/2604.23072/) (2026)
- [Max It or Miss It: Benchmarking LLM On Solving Extremal Problems](https://mlsanity.com/paper/2510.12997/) (2025)
- [Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling](https://mlsanity.com/paper/2605.12411/) (2026)
- [Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response](https://mlsanity.com/paper/2605.30680/) (2026)
- [Learn to Match: Two-Sided Matching with Temporally Extended Feedback](https://mlsanity.com/paper/2606.06744/) (2026)
- [Grounded, Compute-Efficient LLM Policy Agents for Energy-Poverty Equity in Physically-Constrained Peer-to-Peer Energy Markets](https://mlsanity.com/paper/2609.01918/) (2026)
- [Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic Approach](https://mlsanity.com/paper/2609.07749/) (2026)
- [HouseholdBench: Evaluating Large Language Models as Predictors of Household Economic Behavior](https://mlsanity.com/paper/2610.07563/) (2026)
- [The Wealth of Agents: Scaling Agentic AI Across Developers](https://mlsanity.com/paper/2610.20518/) (2026)

## Abstract (arXiv)

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.