Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II

TL;DR

Adaptive Command integrates large language models with behavior trees to enable real-time strategic decision-making and natural language interaction in StarCraft II, improving human-AI collaboration and strategic adaptability.

Contribution

This work introduces a novel framework combining LLMs and behavior trees for real-time decision-making in complex environments, enhancing human-AI collaboration.

Findings

Significant improvement in player decision-making and strategy adaptation

Enhanced support for novice players and players with disabilities

Effective natural language interface with speech capabilities

Abstract

We present Adaptive Command, a novel framework integrating large language models (LLMs) with behavior trees for real-time strategic decision-making in StarCraft II. Our system focuses on enhancing human-AI collaboration in complex, dynamic environments through natural language interactions. The framework comprises: (1) an LLM-based strategic advisor, (2) a behavior tree for action execution, and (3) a natural language interface with speech capabilities. User studies demonstrate significant improvements in player decision-making and strategic adaptability, particularly benefiting novice players and those with disabilities. This work contributes to the field of real-time human-AI collaborative decision-making, offering insights applicable beyond RTS games to various complex decision-making scenarios.