EconAI: Dynamic Persona Evolution and Memory-Aware Agents in Evolving Economic Environments

2026-05-13

AI Summary

This work addresses the limitations of current large language model–driven economic simulations, which struggle to balance short-term optimization with long-term strategic planning and inadequately capture economic sentiment, market volatility, and goal-directed individual behaviors. To overcome these challenges, the authors propose a novel agent-based framework that unifies macro- and microeconomic environments for the first time. By integrating an Economic Sentiment Index (ESI), memory-weighted decision mechanisms, dynamic personality evolution, and coupled work–consumption behavior modeling, agents adaptively adjust their decisions in response to market signals and long-term objectives. This approach significantly enhances the stability of economic responses, more accurately reproduces real-world employment–consumption cycles, and improves both the human-likeness and robustness of agent decision-making.

Abstract

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.

Problem

• agent-based modeling
• economic simulation
• adaptive behavior
• long-term planning
• market volatility

Innovation

• EconAI
• economic sentiment indexing
• memory-aware agents
• dynamic persona evolution
• LLM-powered economic simulation