A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910842292797440 |
|---|---|
| author | Hao, Yuzhi Xie, Danyang |
| author_facet | Hao, Yuzhi Xie, Danyang |
| contents | This paper pioneers a novel approach to economic and public policy analysis by leveraging multiple Large Language Models (LLMs) as heterogeneous artificial economic agents. We first evaluate five LLMs' economic decision-making capabilities in solving two-period consumption allocation problems under two distinct scenarios: with explicit utility functions and based on intuitive reasoning. While previous research has often simulated heterogeneity by solely varying prompts, our approach harnesses the inherent variations in analytical capabilities across different LLMs to model agents with diverse cognitive traits. Building on these findings, we construct a Multi-LLM-Agent-Based (MLAB) framework by mapping these LLMs to specific educational groups and corresponding income brackets. Using interest-income taxation as a case study, we demonstrate how the MLAB framework can simulate policy impacts across heterogeneous agents, offering a promising new direction for economic and public policy analysis by leveraging LLMs' human-like reasoning capabilities and computational power. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16879 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis Hao, Yuzhi Xie, Danyang Artificial Intelligence General Economics Economics This paper pioneers a novel approach to economic and public policy analysis by leveraging multiple Large Language Models (LLMs) as heterogeneous artificial economic agents. We first evaluate five LLMs' economic decision-making capabilities in solving two-period consumption allocation problems under two distinct scenarios: with explicit utility functions and based on intuitive reasoning. While previous research has often simulated heterogeneity by solely varying prompts, our approach harnesses the inherent variations in analytical capabilities across different LLMs to model agents with diverse cognitive traits. Building on these findings, we construct a Multi-LLM-Agent-Based (MLAB) framework by mapping these LLMs to specific educational groups and corresponding income brackets. Using interest-income taxation as a case study, we demonstrate how the MLAB framework can simulate policy impacts across heterogeneous agents, offering a promising new direction for economic and public policy analysis by leveraging LLMs' human-like reasoning capabilities and computational power. |
| title | A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis |
| topic | Artificial Intelligence General Economics Economics |
| url | https://arxiv.org/abs/2502.16879 |