Self Generated Wargame AI: Double Layer Agent Task Planning Based on Large Language Model

TL;DR

This paper introduces a novel agent architecture centered on large language models for decision-making, utilizing a two-layer task planning approach and wargame simulations to demonstrate superior decision-making capabilities over traditional AI methods.

Contribution

It innovatively applies large language models to intelligent decision-making with a two-layer agent planning framework and validates its effectiveness through wargame simulations.

Findings

Large language models outperform reinforcement learning and rule-based AI in decision-making.

Decision-making ability is highly influenced by prompt design.

The approach extends LLM applications from human-computer interaction to autonomous decision-making.

Abstract

The large language models represented by ChatGPT have a disruptive impact on the field of artificial intelligence. But it mainly focuses on natural language processing, speech recognition, machine learning and natural language understanding. This paper innovatively applies the large language model to the field of intelligent decision-making, places the large language model in the decision-making center, and constructs an agent architecture with the large language model as the core. Based on this, it further proposes a two-layer agent task planning, issues and executes decision commands through the interaction of natural language, and carries out simulation verification through the wargame simulation environment. Through the game confrontation simulation experiment, it is found that the intelligent decision-making ability of the large language model is significantly stronger than the commonly used reinforcement learning AI and rule AI, and the intelligence, understandability and generalization are all better. And through experiments, it was found that the intelligence of the large language model is closely related to prompt. This work also extends the large language model from previous human-computer interaction to the field of intelligent decision-making, which has important reference value and significance for the development of intelligent decision-making.