SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent

TL;DR

This paper introduces SRAP-Agent, a novel framework that leverages large language models to simulate and optimize scarce resource allocation policies, addressing limitations of traditional methods and improving policy effectiveness in real-world scenarios.

Contribution

The paper presents an innovative LLM-based simulation framework for resource allocation, bridging the gap between theoretical models and real-world complexities.

Findings

SRAP-Agent effectively simulates public housing allocation scenarios.

The framework improves policy optimization compared to traditional methods.

Source code is publicly available for reproducibility.

Abstract

Public scarce resource allocation plays a crucial role in economics as it directly influences the efficiency and equity in society. Traditional studies including theoretical model-based, empirical study-based and simulation-based methods encounter limitations due to the idealized assumption of complete information and individual rationality, as well as constraints posed by limited available data. In this work, we propose an innovative framework, SRAP-Agent (Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent), which integrates Large Language Models (LLMs) into economic simulations, aiming to bridge the gap between theoretical models and real-world dynamics. Using public housing allocation scenarios as a case study, we conduct extensive policy simulation experiments to verify the feasibility and effectiveness of the SRAP-Agent and employ the Policy Optimization Algorithm with certain optimization objectives. The source code can be found in https://github.com/jijiarui-cather/SRAPAgent_Framework