Saved in:
Bibliographic Details
Main Authors: Liu, Annie, Cao, Zane, Chen, Lang, Xu, Zongxin, Wang, Zigan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.13762
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918500128260096
author Liu, Annie
Cao, Zane
Chen, Lang
Xu, Zongxin
Wang, Zigan
author_facet Liu, Annie
Cao, Zane
Chen, Lang
Xu, Zongxin
Wang, Zigan
contents The integration of large language models (LLMs) in economic simulations has significantly enhanced agent-based modeling, yet existing frameworks struggle to capture the interplay between short-term optimization and long-term strategic planning. Conventional approaches rely on static data-driven predictions, failing to incorporate adaptive behaviors influenced by economic sentiment, market volatility, and individual goals. To address these limitations, we introduce a novel EconAI framework, incorporating economic sentiment indexing (ESI), memory weighting, and dynamic decision-making mechanisms. By quantifying economic belief, adjusting historical data influence, and linking work-consumption behaviors, EconAI achieves a more human-like decision process, where agents adapt their actions based on both market signals and long-term objectives. It is the first LLM-powered simulation system that can simulate the macro/microeconomic environment and interactions in a unified framework. Empirical evaluations show that EconAI improves stability in economic responses, better replicates real-world employment-consumption cycles, and enhances overall decision robustness. This advancement marks a crucial step towards more realistic, adaptive economic agent simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13762
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EconAI: Dynamic Persona Evolution and Memory-Aware Agents in Evolving Economic Environments
Liu, Annie
Cao, Zane
Chen, Lang
Xu, Zongxin
Wang, Zigan
Multiagent Systems
The integration of large language models (LLMs) in economic simulations has significantly enhanced agent-based modeling, yet existing frameworks struggle to capture the interplay between short-term optimization and long-term strategic planning. Conventional approaches rely on static data-driven predictions, failing to incorporate adaptive behaviors influenced by economic sentiment, market volatility, and individual goals. To address these limitations, we introduce a novel EconAI framework, incorporating economic sentiment indexing (ESI), memory weighting, and dynamic decision-making mechanisms. By quantifying economic belief, adjusting historical data influence, and linking work-consumption behaviors, EconAI achieves a more human-like decision process, where agents adapt their actions based on both market signals and long-term objectives. It is the first LLM-powered simulation system that can simulate the macro/microeconomic environment and interactions in a unified framework. Empirical evaluations show that EconAI improves stability in economic responses, better replicates real-world employment-consumption cycles, and enhances overall decision robustness. This advancement marks a crucial step towards more realistic, adaptive economic agent simulations.
title EconAI: Dynamic Persona Evolution and Memory-Aware Agents in Evolving Economic Environments
topic Multiagent Systems
url https://arxiv.org/abs/2605.13762