Want To Choose Your Own Adventure? Then First Make a Plan.

Abstract

Our research demonstrates that Large Language Models (LLMs) can successfully be used for automated story generation provided that they are first given a valid input plan that has been generated by an automated planner. A well-known issue with LLMs is that while they can generate coherent outputs over short spans of text, they lose coherence when they are asked to produce longer text narratives. In this study, we combine the fields of Automated Planning and Text Generation to show how text-based interactive Choose Your Own Adventure (CYOA) stories can be created using LLMs in conjunction with Fully Observable Non-Deterministic (FOND) based Automated Planning.

Publication
The 37th Canadian Conference on Artificial Intelligence (Canadian AI)
Date
Links
PDF