EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities
2023/10/16 by Nian Li, Li, Nian, Chen Gao +6 · 63 citations
Decision Sciences · Engineering · #Artificial Intelligence (cs.AI) #Energy Load and Power Forecasting #FOS: Computer and information sciences #Stock Market Forecasting Methods
paper · pdf · doi:10.48550/arxiv.2310.10436
openalex publication_date 2023/10/16 · openalex created_date 2023/10/18 · openalex updated_date 2026/07/28
Abstract
The advent of artificial intelligence has led to a growing emphasis on data-driven modeling in macroeconomics, with agent-based modeling (ABM) emerging as a prominent bottom-up simulation paradigm. In ABM, agents (e.g., households, firms) interact within a macroeconomic environment, collectively generating market dynamics. Existing agent modeling typically employs predetermined rules or learning-based neural networks for decision-making. However, customizing each agent presents significant challenges, complicating the modeling of agent heterogeneity. Additionally, the influence of multi-period market dynamics and multifaceted macroeconomic factors are often overlooked in decision-making processes. In this work, we introduce EconAgent, a large language model-empowered agent with human-like characteristics for macroeconomic simulation. We first construct a simulation environment that incorporates various market dynamics driven by agents' decisions regarding work and consumption. Through the perception module, we create heterogeneous agents with distinct decision-making mechanisms. Furthermore, we model the impact of macroeconomic trends using a memory module, which allows agents to reflect on past individual experiences and market dynamics. Simulation experiments show that EconAgent can make realistic decisions, leading to more reasonable macroeconomic phenomena compared to existing rule-based or learning-based agents. Our codes are released at https://github.com/tsinghua-fib-lab/ACL24-EconAgent.
Cited by
- An Information-Theoretic Framework for Robust Large Language Model Editing
- Generative AI as Digital Representatives in Collective Decision-Making: A Game-Theoretical Approach
- MASim: Multilingual Agent-Based Simulation for Social Science
- When AI Agents Compete for Jobs: Strategic Capabilities and Economic Dynamics of AI Labour Markets
- Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems
- The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems
- Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making
- InsurAgent: A Large Language Model-Empowered Agent for Simulating Individual Behavior in Purchasing Flood Insurance
- Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments
- Eco3S: Complex Socio-Economic System Simulation via Agent-Based Models
- Diagon: A Programmable Testbed for AI-Agent Cognitive Labor Markets
- Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
- Fetch.ai: An Architecture for Modern Multi-Agent Systems
- DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
- Addressing the alignment problem in transportation policy making: an LLM approach
- Agent-Based Simulation of a Financial Market with Large Language Models
- StoryBox: Collaborative Multi-Agent Simulation for Hybrid Bottom-Up Long-Form Story Generation Using Large Language Models
- Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces
- SimCity: Multi-Agent Urban Development Simulation with Rich Interactions
- Stochastic Self-Organization in Multi-Agent Systems
- Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management
- The Emergence of Altruism in Large-Language-Model Agents Society
- Generalized Multi-agent Social Simulation Framework
- Reimagining Agent-based Modeling with Large Language Model Agents via Shachi
- Enhancing LLM-Based Social Bot via an Adversarial Learning Framework
- Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and Humans
- Rationality Check! Benchmarking the Rationality of Large Language Models
- From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
- ShortageSim: Simulating Drug Shortages under Information Asymmetry
- EconAgentic in DePIN Markets: A Large Language Model Approach to the Sharing Economy of Decentralized Physical Infrastructure
- Bridging Minds and Machines: Toward an Integration of AI and Cognitive Science
- Bias-Adjusted LLM Agents for Human-Like Decision-Making via Behavioral Economics
- The Roots of International Perceptions: Simulating US Attitude Changes Towards China with LLM Agents
- Simulating Generative Social Agents via Theory-Informed Workflow Design
- Exploring Large Language Model Agents for Piloting Social Experiments
- Simulating Human-Like Learning Dynamics with LLM-Empowered Agents
- Tree-of-Reasoning: Towards Complex Medical Diagnosis via Multi-Agent Reasoning with Evidence Tree
- A Survey on AgentOps: Categorization, Challenges, and Future Directions
- LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
- An Explainable Emotion Alignment Framework for LLM-Empowered Agent in Metaverse Service Ecosystem
- A Comprehensive Review of Human Error in Risk-Informed Decision Making: Integrating Human Reliability Assessment, Artificial Intelligence, and Human Performance Models
- A Survey of Large Language Models in Discipline-specific Research: Challenges, Methods and Opportunities
- InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior
- Large Language Models for Agent-Based Modelling: Current and possible uses across the modelling cycle
- What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents
- AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles
- Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications
- GATSim: Urban Mobility Simulation with Generative Agents
- Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models
- A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures
- LLM-Based Social Simulations Require a Boundary
- Augmenting Multi-Agent Communication with State Delta Trajectory
- Modeling Earth-Scale Human-Like Societies with One Billion Agents
- IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment
- EconGym: A Scalable AI Testbed with Diverse Economic Tasks
- Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives
- CrimeMind: Simulating Urban Crime with Multi-Modal LLM Agents
- Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling
- AI Agent Behavioral Science
- TaxAgent: How Large Language Model Designs Fiscal Policy
- Open-Set Living Need Prediction with Large Language Models
- LocalGPT: Benchmarking and Advancing Large Language Models for Local Life Services in Meituan
- Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Related