Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II
By: Weiyu Ma , Dongyu Xu , Shu Lin and more
Potential Business Impact:
Helps players win video games using talking.
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.
Similar Papers
Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning
Artificial Intelligence
AI learns to win complex video games.
Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models
Human-Computer Interaction
Lets players "program" game actions with words.
SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks
Machine Learning (CS)
Helps AI learn to play complex games better.