HAMLET: A Hierarchical and Adaptive Multi-Agent Framework for Live Embodied Theatrics

Researchers have developed HAMLET, a hierarchical multi-agent AI framework that creates immersive, interactive theatrical experiences using large language models. The system generates narrative blueprints from simple topics and enables AI actors to perform with adaptive reasoning, emotional states, and physical interactions with scene props.

• →HAMLET addresses limitations of existing LLM-based drama generation by adding initiative and physical scene interaction capabilities.
• →The framework operates in two phases: offline narrative blueprint generation and real-time online performance with multi-agent actors.
• →AI actors use adaptive reasoning modules to make decisions based on personas, memories, goals, and emotional states during group interactions.
• →The system enables embodied interactions where actors can manipulate scene props like opening letters or picking up weapons.
• →Researchers introduced HAMLETJudge, a specialized critic model for automated evaluation of theatrical performance quality.