On Improvisation and Open-Endedness: Insights for Experiential AI

2025-11-01

AI Summary

This study investigates whether AI can achieve genuine open-ended improvisation and establishes a rigorous evaluation framework for it. Method: Drawing on in-depth interviews with human improvisers in dance, music, and related domains, the authors identify core improvisational qualities—including active listening, presence, embracing uncertainty, nonjudgmental flow, and balance between structure and surprise—and integrate them into a practice-oriented framework bridging human improvisational art and AI’s open-ended development. Combining qualitative analysis with AI design principles, the work introduces mechanisms for active perception, dynamical equilibrium within edge-of-chaos regimes, empathic modeling, intrinsically motivated action selection, and cross-modal metaphor generation to support embodied improvisational AI agents. Contribution/Results: The study endows generative AI with creative evolutionary capacity, yielding transferable improvisation design principles and providing both theoretical foundations and implementable pathways for human–AI collaborative improvisation.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Intelligent Robots: Embodied AI
• Philosophy and Ethics of AI: Artificial General Intelligence

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Improvisation-the art of spontaneous creation that unfolds moment-to-moment without a scripted outcome-requires practitioners to continuously sense, adapt, and create anew. It is a fundamental mode of human creativity spanning music, dance, and everyday life. The open-ended nature of improvisation produces a stream of novel, unrepeatable moments-an aspect highly valued in artistic creativity. In parallel, open-endedness (OE)-a system's capacity for unbounded novelty and endless "interestingness"-is exemplified in natural or cultural evolution and has been considered "the last grand challenge" in artificial life (ALife). The rise of generative AI now raises the question in computational creativity (CC) research: What makes a "good" improvisation for AI? Can AI learn to improvise in a genuinely open-ended way? In this work-in-progress paper, we report insights from in-depth interviews with 6 experts in improvisation across dance, music, and contact improvisation. We draw systemic connections between human improvisational arts and the design of future experiential AI agents that could improvise alone or alongside humans-or even with other AI agents-embodying qualities of improvisation drawn from practice: active listening (umwelt and awareness), being in the time (mindfulness and ephemerality), embracing the unknown (source of randomness and serendipity), non-judgmental flow (acceptance and dynamical stability, balancing structure and surprise (unpredictable criticality at edge of chaos), imaginative metaphor (synaesthesia and planning), empathy, trust, boundary, and care (mutual theory of mind), and playfulness and intrinsic motivation (maintaining interestingness).

Problem

• Exploring AI's capacity for genuine improvisation and open-ended creativity
• Bridging human improvisational arts with experiential AI agent design
• Investigating key qualities like mindfulness and unpredictability for AI improvisation

Innovation

• AI agents learn improvisation from human experts
• System connects human improvisation arts to AI design
• Embodies qualities like active listening and mindfulness