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

Teddy Lazebnik; Labib Shami

doi:10.48550/arXiv.2501.18177

Preprint / working paper · 2025

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

Teddy Lazebnik and Labib Shami

arXiv Preprint

Read on arXiv

Summary

Asks how tax evasion emerges in a population in the first place, rather than taking it as given. The study uses an agent-based simulation whose agents are driven by a large language model and deep reinforcement learning.

This summary was written for this website from the published abstract. The publisher’s abstract and full text are the authoritative versions. No full text is reproduced here.

Research theme

The non-observed economy

Related publications

Tell Me Who Your Neighbors Are and I Will Tell You Your Informal Economy Size: The Case of Sweden · Computational Economics, 2026
Informal self-employment within the non-observed economy of Israel · International Journal of Entrepreneurship and Small Business, 2024
Implementing Machine Learning Methods in Estimating the Size of the Non-observed Economy · Computational Economics, 2024
Microfounded Tax Revenue Forecast Model with Heterogeneous Population and Genetic Algorithm Approach · Computational Economics, 2024

Related policy analysis

The Non-Observed Economy in Israel · Taub Center, 2020

All publications

Details

Type: Preprint / working paper
Status: Preprint
Venue: arXiv
Online: 30 January 2025
DOI: 10.48550/arXiv.2501.18177
Access: Freely available preprint

Cite

Lazebnik, T., & Shami, L. (2025). Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulation. arXiv. https://doi.org/10.48550/arXiv.2501.18177

BibTeX

@misc{lazebnik2025investigating,
  author = {Lazebnik, Teddy and Shami, Labib},
  title = {Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulation},
  year = {2025},
  eprint = {2501.18177},
  archiveprefix = {arXiv},
  howpublished = {arXiv preprint},
  doi = {10.48550/arXiv.2501.18177}
}