# dAIrector: Automatic Story Beat Generation through Knowledge Synthesis

arXiv: https://arxiv.org/abs/1811.03423 · HTML: https://mlsanity.com/paper/1811.03423/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2018.

## Built on by (most cited first, 4 of 4)

- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [Learning Norms from Stories: A Prior for Value Aligned Agents](https://mlsanity.com/paper/1912.03553/) (2019)
- [Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior](https://mlsanity.com/paper/2104.09469/) (2021)
- [Collaborative Storytelling with Human Actors and AI Narrators](https://mlsanity.com/paper/2109.14728/) (2021)

## Abstract (arXiv)

dAIrector is an automated director which collaborates with humans storytellers for live improvisational performances and writing assistance. dAIrector can be used to create short narrative arcs through contextual plot generation. In this work, we present the system architecture, a quantitative evaluation of design choices, and a case-study usage of the system which provides qualitative feedback from a professional improvisational performer. We present relevant metrics for the understudied domain of human-machine creative generation, specifically long-form narrative creation. We include, alongside publication, open-source code so that others may test, evaluate, and run the dAIrector.