Abstract technology is an essential part of efficient decision-making in artificial intelligence research and has been widely used in large-scale decision-making problems. Although Monte Carlo tree search has achieved impressive results in many decision-making fields, it faces challenges of a vast decision space and long planning cycles in real-world decision-making problems. This paper investigates the application of abstract technology in Monte Carlo tree search and analyzes how it can enhance the decision-making ability of Monte Carlo tree search from the perspectives of state space and action space. Additionally, this paper provides further insights into the problems that still need to be addressed and future research directions in the study of abstract Monte Carlo tree search.