ImprovMate: Multimodal AI Assistant for Improv Actor Training
Riccardo Drago, Yotam Sechayk, Mustafa Doga Dogan, Andrea Sanna, Takeo Igarashi

TL;DR
ImprovMate is a multimodal AI assistant that uses large language models to generate narrative cues, aiding improv actors in training by maintaining coherence and reducing cognitive load, thus enhancing traditional improvisation exercises.
Contribution
This paper introduces ImprovMate, a novel AI tool leveraging LLMs to automate improv training cues, integrating professional insights and structured exercises for improved actor training.
Findings
Actors are receptive to AI-assisted improv training.
ImprovMate successfully maintains narrative coherence during exercises.
Participants appreciated the AI-generated cues as a fresh training approach.
Abstract
Improvisation training for actors presents unique challenges, particularly in maintaining narrative coherence and managing cognitive load during performances. Previous research on AI in improvisation performance often predates advances in large language models (LLMs) and relies on human intervention. We introduce ImprovMate, which leverages LLMs as GPTs to automate the generation of narrative stimuli and cues, allowing actors to focus on creativity without keeping track of plot or character continuity. Based on insights from professional improvisers, ImprovMate incorporates exercises that mimic live training, such as abrupt story resolution and reactive thinking exercises, while maintaining coherence via reference tables. By balancing randomness and structured guidance, ImprovMate provides a groundbreaking tool for improv training. Our pilot study revealed that actors might embrace AI…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
