Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time

TL;DR

This paper introduces a Hierarchical Expert Prompt (HEP) for large language models to enhance decision-making in complex environments like StarCraft II, successfully defeating top-tier AI agents and outperforming baseline methods.

Contribution

The paper presents a novel hierarchical prompting framework that incorporates expert-level tactical knowledge to improve LLM performance in complex decision tasks.

Findings

Defeated Elite AI in TextStarCraft II for the first time

Outperformed baseline methods across various difficulty levels

Demonstrated practical effectiveness in complex decision-making

Abstract

Since the emergence of the Large Language Model (LLM), LLM has been widely used in fields such as writing, translating, and searching. However, there is still great potential for LLM-based methods in handling complex tasks such as decision-making in the StarCraft II environment. To address problems such as lack of relevant knowledge and poor control over subtasks of varying importance, we propose a Hierarchical Expert Prompt (HEP) for LLM. Our method improves the understanding of game situations through expert-level tactical knowledge, improving the processing quality of tasks of varying importance through a hierarchical framework. Our approach defeated the highest level (Elite) standard built-in agent in TextStarCraft II for the first time and consistently outperformed the baseline method in other difficulties. Our experiments suggest that the proposed method is a practical solution for tackling complex decision-making challenges. The replay video can be viewed on https://www.bilibili.com/video/BV1uz42187EF and https://youtu.be/dO3PshWLV5M, and our codes have been open-sourced on https://github.com/luchang1113/HEP-LLM-play-StarCraftII.