ProcureGym: A Multi-Agent Markov Game Framework for Modeling National Volume-based Drug Procurement
This provides a data-driven tool for assessing policy impacts and formulating procurement strategies in pharmaceutical markets, though it is an incremental application of existing methods to a new domain.
The paper tackles the problem of modeling China's National Volume-Based Drug Procurement (NVBP) by introducing ProcureGym, a multi-agent Markov game simulation platform based on real-world data from 7 rounds covering 325 drugs and 2,267 firms, where RL agents achieved superior winner alignment and profits compared to LLM and rule-based algorithms.
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.