This research introduces HRT-ML, a framework that leverages Large Language Models to create robots that adapt their communication style based on human needs and task complexity.

• Replaces rigid, pre-determined robot communication with adaptive support that responds to changing situations
• Enables robots to provide strategic guidance and task-specific instructions through multimodal language feedback
• Demonstrates improved team performance in complex collaborative tasks
• Represents a significant advancement in making human-robot collaboration more natural and effective

For engineering teams, this research offers a practical path to creating more intuitive robotic assistants that can adjust their support level based on human expertise and task requirements, potentially accelerating adoption in industrial and service applications.

Effect of Adaptive Communication Support on LLM-powered Human-Robot Collaboration