STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game
This addresses the challenge of creating dynamic, player-driven interactive fiction games, offering a novel approach to game generation, though it is incremental in advancing LLM applications in this domain.
The authors tackled the problem of generating interactive fiction games by using Large Language Models to create stories, populate worlds, and build code for actions, enabling open-ended story generation with grounded gameplay. They achieved a success rate in action code generation that allowed players to interactively play through entire generated stories.
We introduce STORY2GAME, a novel approach to using Large Language Models to generate text-based interactive fiction games that starts by generating a story, populates the world, and builds the code for actions in a game engine that enables the story to play out interactively. Whereas a given set of hard-coded actions can artificially constrain story generation, the ability to generate actions means the story generation process can be more open-ended but still allow for experiences that are grounded in a game state. The key to successful action generation is to use LLM-generated preconditions and effects of actions in the stories as guides for what aspects of the game state must be tracked and changed by the game engine when a player performs an action. We also introduce a technique for dynamically generating new actions to accommodate the player's desire to perform actions that they think of that are not part of the story. Dynamic action generation may require on-the-fly updates to the game engine's state representation and revision of previously generated actions. We evaluate the success rate of action code generation with respect to whether a player can interactively play through the entire generated story.