ProcureGym: A Multi-Agent Markov Game Framework for Modeling National Volume-based Drug Procurement

TL;DR

ProcureGym is a high-fidelity multi-agent simulation platform modeling China's drug procurement as a Markov Game, enabling evaluation of different agent strategies and policy impacts based on real-world data.

Contribution

We developed ProcureGym, a novel simulation environment for China's NVBP, integrating real data and diverse agent models to analyze strategic procurement behaviors.

Findings

RL agents outperform rule-based models in profits and alignment

Maximum bid price and procurement volume are key strategic factors

The platform effectively assesses policy impacts and strategic outcomes

Abstract

In this paper, we introduce ProcureGym, an data-driven multi-agent simulation platform that models China's National Volume-Based drug Procurement (NVBP) as a Markov Game. Based on real-world data from 7 rounds of NVBP (covering 325 drugs and 2,267 firms), the platform establishes a high-fidelity simulation environment. Within this framework, we evaluate diverse agent models, including Reinforcement Learning (RL), Large Language Model (LLM), and Rule-based algorithms. Experimental results demonstrate that RL agents achieve superior winner alignment and profits. Further analyses show that maximum valid bidding price and procurement volume dominate strategic outcomes. ProcureGym thus serves as a rigorous instrument for assessing policy impacts and formulating future procurement strategies.