Directing Space: Rehearsing Architecture as Performer with Explainable AI

TL;DR

This paper presents a rehearsal-oriented prototype system where AI mediates interactive architecture as a performative agent, enabling real-time environmental adaptations in immersive artistic performances through explainable AI and spatial sensing.

Contribution

It introduces a novel system that integrates large language models with physical performance spaces, fostering creative collaboration between artists and AI in live rehearsals.

Findings

Prototype supports real-time spatial and speech-based environmental adaptations.

Enables iterative experimentation and dramaturgically grounded architectural interactions.

Facilitates creative dialogue between artists and AI agents in immersive environments.

Abstract

As AI systems increasingly become embedded in interactive and im-mersive artistic environments, artists and technologists are discovering new opportunities to engage with their interpretive and autonomous capacities as creative collaborators in live performance. The focus of this work-in-progress is on outlining conceptual and technical foundations under which performance-makers and interactive architecture can collaborate within rehearsal settings. It introduces a rehearsal-oriented prototype system for shaping and testing AI-mediated environments within creative practice. This approach treats interactive architecture as a performative agent that senses spatial behaviour and speech, interprets these signals through a large language model, and generates real-time environmental adaptations. Designed for deployment in physical performance spaces, the system employs virtual blueprints to support iterative experimentation and creative dialogue between artists and AI agents, using reasoning traces to inform architectural interaction design grounded in dramaturgical principles.