BERALL: Towards Generating Retrieval-augmented State-based Interactive Fiction Games

Abstract

Interactive fiction (IF) games are a genre of games where the player interacts with the fictional world via text-based commands, solving puzzles primarily by exploring the world and using items they collect along the way. Although there has been much work on playing IF using AI, there is relatively less work on the creation of such games using AI. While large language models (LLMs) have made the generation of text far easier in the past several years, they still struggle to generate the highly-structured and consistent story worlds that one might see in IF. We present a threepart system called BERALL, which generates unique text adventure games by 1) maintaining the current state of the story world, 2) using retrieval-augmented generation (RAG) to create relevant location descriptions, and 3) combining these components to create a coherent experience for the player. Our approach is effective at generating room and story descriptions from the setting and knowledge graphs, demonstrating the potential benefits of LLMs in IF generation. We find challenges remain in maintaining the current game state due, in part, to LLMs not understanding the impact of changes to the knowledge graph generated by the player’s command.