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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ma, Weiyu, Xu, Dongyu, Lin, Shu, Zhang, Haifeng, Wang, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912784354115584
author Ma, Weiyu
Xu, Dongyu
Lin, Shu
Zhang, Haifeng
Wang, Jun
author_facet Ma, Weiyu
Xu, Dongyu
Lin, Shu
Zhang, Haifeng
Wang, Jun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16580
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II
Ma, Weiyu
Xu, Dongyu
Lin, Shu
Zhang, Haifeng
Wang, Jun
Human-Computer Interaction
Artificial Intelligence
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.
title Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2508.16580