Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulation

2025-01-30

AI Summary

This study investigates the spontaneous emergence of tax evasion within populations and its role in driving the growth of the informal economy. Method: We propose a “behavioral self-emergence” paradigm and develop a novel multi-agent simulation framework integrating large language models (for behavioral generation and narrative understanding) with deep Q-network (DQN) reinforcement learning—enabling tax evasion to evolve endogenously without pre-specified rules. Contribution/Results: We identify and quantify the synergistic effects of four key factors—individual personality traits, social narratives, enforcement probability, and public-good efficacy—on evasion dynamics. Our analysis demonstrates that only the joint enhancement of enforcement and public-good provision effectively suppresses evasion; isolated interventions yield limited impact. We further quantify the relative influence of each factor on both the onset timing and scale of evasion. The framework provides a computationally tractable and interpretable theoretical foundation for evidence-based governance of the informal economy.

Technology Category

• Game Theory and Economic Paradigms: Behavioral Game Theory
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Humans and AI: Learning Human Values and Preferences

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Tax evasion, usually the largest component of an informal economy, is a persistent challenge over history with significant socio-economic implications. Many socio-economic studies investigate its dynamics, including influencing factors, the role and influence of taxation policies, and the prediction of the tax evasion volume over time. These studies assumed such behavior is given, as observed in the real world, neglecting the"big bang"of such activity in a population. To this end, computational economy studies adopted developments in computer simulations, in general, and recent innovations in artificial intelligence (AI), in particular, to simulate and study informal economy appearance in various socio-economic settings. This study presents a novel computational framework to examine the dynamics of tax evasion and the emergence of informal economic activity. Employing an agent-based simulation powered by Large Language Models and Deep Reinforcement Learning, the framework is uniquely designed to allow informal economic behaviors to emerge organically, without presupposing their existence or explicitly signaling agents about the possibility of evasion. This provides a rigorous approach for exploring the socio-economic determinants of compliance behavior. The experimental design, comprising model validation and exploratory phases, demonstrates the framework's robustness in replicating theoretical economic behaviors. Findings indicate that individual personality traits, external narratives, enforcement probabilities, and the perceived efficiency of public goods provision significantly influence both the timing and extent of informal economic activity. The results underscore that efficient public goods provision and robust enforcement mechanisms are complementary; neither alone is sufficient to curtail informal activity effectively.

Problem

• Tax Evasion
• Informal Economy
• Compliance Mechanisms

Innovation

• Super Language Model
• Advanced Learning Techniques
• Spontaneous Informal Economy Simulation