BIMSA >
BIMSA Digital Economy Lab Seminar
EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities
EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities
Organizers
Speaker
Time
Monday, December 2, 2024 3:20 PM - 4:20 PM
Venue
A3-2-303
Online
Zoom 230 432 7880
(BIMSA)
Abstract
This talk will introduce EconAgent, a large language model-empowered agent with human-like characteristics for macroeconomic simulation. First, a simulation environment is constructed which incorporates various market dynamics driven by agents’ decisions regarding work and consumption. Through the perception module, heterogeneous agents with distinct decision-making mechanisms are created. Furthermore, the impact of macroeconomic trends is modeled using a memory module, allowing the 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.
Speaker Intro
Xueda Wei is a PHD student at BIMSA and RUC. Her research interests including digital economy, complex network theory and applied systems.