# Word2World: Generating Stories and Worlds through Large Language Models

arXiv: https://arxiv.org/abs/2405.06686 · HTML: https://mlsanity.com/paper/2405.06686/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 6 May 2024.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions](https://mlsanity.com/paper/1901.01753/) (2019)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [Learning to Speak and Act in a Fantasy Text Adventure Game](https://mlsanity.com/paper/1903.03094/) (2019)
- [Replay-Guided Adversarial Environment Design](https://mlsanity.com/paper/2110.02439/) (2021)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization](https://mlsanity.com/paper/2306.01102/) (2023)
- [Deep Learning for Procedural Content Generation](https://mlsanity.com/paper/2010.04548/) (2020)
- [Super Mario as a String: Platformer Level Generation Via LSTMs](https://mlsanity.com/paper/1603.00930/) (2016)
- [The Chess Transformer: Mastering Play using Generative Language Models](https://mlsanity.com/paper/2008.04057/) (2020)
- [Bootstrapping Conditional GANs for Video Game Level Generation](https://mlsanity.com/paper/1910.01603/) (2019)
- [Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence](https://mlsanity.com/paper/2210.07109/) (2022)
- [Game Generation via Large Language Models](https://mlsanity.com/paper/2404.08706/) (2024)
- [Generating Interactive Worlds with Text](https://mlsanity.com/paper/1911.09194/) (2019)
- [The Go Transformer: Natural Language Modeling for Game Play](https://mlsanity.com/paper/2007.03500/) (2020)
- [The Ink Splotch Effect: A Case Study on ChatGPT as a Co-Creative Game Designer](https://mlsanity.com/paper/2403.02454/) (2024)
- [Hierarchically Composing Level Generators for the Creation of Complex Structures](https://mlsanity.com/paper/2302.01561/) (2023)
- [Augmentative Topology Agents For Open-Ended Learning](https://mlsanity.com/paper/2210.11442/) (2022)

## Built on by (most cited first, 18 of 18)

- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games](https://mlsanity.com/paper/2602.17594/) (2026)
- [DreamGarden: A Designer Assistant for Growing Games from a Single Prompt](https://mlsanity.com/paper/2410.01791/) (2024)
- [GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps](https://mlsanity.com/paper/2410.07765/) (2024)
- [WhatELSE: Shaping Narrative Spaces at Configurable Level of Abstraction for AI-bridged Interactive Storytelling](https://mlsanity.com/paper/2502.18641/) (2025)
- [Grammar-based Game Description Generation using Large Language Models](https://mlsanity.com/paper/2407.17404/) (2024)
- [STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game](https://mlsanity.com/paper/2505.03547/) (2025)
- [Vox Deorum: A Hybrid LLM Architecture for 4X / Grand Strategy Game AI -- Lessons from Civilization V](https://mlsanity.com/paper/2512.18564/) (2025)
- [PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning](https://mlsanity.com/paper/2502.10906/) (2025)
- [Word2Minecraft: Generating 3D Game Levels through Large Language Models](https://mlsanity.com/paper/2503.16536/) (2025)
- [GameTileNet: A Semantic Dataset for Low-Resolution Game Art in Procedural Content Generation](https://mlsanity.com/paper/2507.02941/) (2025)
- [Narrative-to-Scene Generation: An LLM-Driven Pipeline for 2D Game Environments](https://mlsanity.com/paper/2509.04481/) (2025)
- [Mortar: Evolving Mechanics for Automatic Game Design](https://mlsanity.com/paper/2601.00105/) (2025)
- [From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation](https://mlsanity.com/paper/2604.25482/) (2026)
- [Breaking the Assistant Mold: Modeling Behavioral Variation in LLM Based Procedural Character Generation](https://mlsanity.com/paper/2601.03396/) (2026)
- [From LLM-Driven Trading Card Generation to Procedural Relatedness: A Pok'emon Case Study](https://mlsanity.com/paper/2604.27972/) (2026)
- [Procedural Content Metageneration via Program Search and Continual Abstraction Discovery](https://mlsanity.com/paper/2608.17947/) (2026)
- [Programmable Cellular Automata](https://mlsanity.com/paper/2609.06102/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have proven their worth across a diverse spectrum of disciplines. LLMs have shown great potential in Procedural Content Generation (PCG) as well, but directly generating a level through a pre-trained LLM is still challenging. This work introduces Word2World, a system that enables LLMs to procedurally design playable games through stories, without any task-specific fine-tuning. Word2World leverages the abilities of LLMs to create diverse content and extract information. Combining these abilities, LLMs can create a story for the game, design narrative, and place tiles in appropriate places to create coherent worlds and playable games. We test Word2World with different LLMs and perform a thorough ablation study to validate each step. We open-source the code at https://github.com/umair-nasir14/Word2World.