HAMLET: Hyperadaptive Agent-based Modeling for Live Embodied Theatrics

2025-07-21

AI Summary

Existing LLM-based dramatic generation approaches suffer from weak agent proactivity, limited physical environment interaction, and dependence on verbose user inputs—hindering real-time immersive performance. This paper proposes a multi-agent improvisational theater framework: given a concise theme, it autonomously generates a narrative blueprint and orchestrates autonomous actor agents modeled on personality, goals, and emotional states. These agents make proactive decisions, manipulate environmental props, and dynamically influence both plot progression and other characters. The system integrates narrative generation, contextual perception, and state-broadcasting mechanisms to enable cross-character dialogue and physical scene intervention. Experiments demonstrate significant improvements in narrative coherence, character expressiveness, and interactive immersion, outperforming baseline methods across multiple quantitative and qualitative metrics. The code and dataset are publicly released.

Technology Category

• Multiagent Systems: Adversarial Agents
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Creating an immersive and interactive theatrical experience is a long-term goal in the field of interactive narrative. The emergence of large language model (LLM) is providing a new path to achieve this goal. However, existing LLM-based drama generation methods often result in AI agents that lack initiative and cannot interact with the physical environment. Furthermore, these methods typically require detailed user input to drive the drama. These limitations reduce the interactivity and immersion of online real-time performance. To address the above challenges, we propose HAMLET, a multi-agent framework focused on drama creation and online performance. Given a simple topic, the framework generates a narrative blueprint, guiding the subsequent improvisational performance. During the online performance, each actor is given an autonomous mind. This means that actors can make independent decisions based on their own background, goals, and emotional state. In addition to conversations with other actors, their decisions can also change the state of scene props through actions such as opening a letter or picking up a weapon. The change is then broadcast to other related actors, updating what they know and care about, which in turn influences their next action. To evaluate the quality of drama performance, we designed an evaluation method to assess three primary aspects, including character performance, narrative quality, and interaction experience. The experimental evaluation shows that HAMLET can create expressive and coherent theatrical experiences. Our code, dataset and models are available at https://github.com/HAMLET-2025/HAMLET.

Problem

• LLM-based drama lacks agent initiative and environment interaction
• Existing methods need excessive user input for drama generation
• Current approaches reduce interactivity and immersion in live performances

Innovation

• Multi-agent framework for drama creation
• Autonomous actors with independent decision-making
• Dynamic prop interaction and state updates