# MarioGPT: Open-Ended Text2Level Generation through Large Language Models

arXiv: https://arxiv.org/abs/2302.05981 · HTML: https://mlsanity.com/paper/2302.05981/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 52 references that are in the map.
- First posted on arXiv 12 Feb 2023.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models](https://mlsanity.com/paper/2205.10770/) (2022)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [Evolution through Large Models](https://mlsanity.com/paper/2206.08896/) (2022)
- [Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space](https://mlsanity.com/paper/1912.02400/) (2019)
- [Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network](https://mlsanity.com/paper/1805.00728/) (2018)
- [Deep Learning for Procedural Content Generation](https://mlsanity.com/paper/2010.04548/) (2020)
- [Level Generation Through Large Language Models](https://mlsanity.com/paper/2302.05817/) (2023)
- [Increasing Generality in Machine Learning through Procedural Content Generation](https://mlsanity.com/paper/1911.13071/) (2019)
- [Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network](https://mlsanity.com/paper/2007.05674/) (2020)
- [The VGLC: The Video Game Level Corpus](https://mlsanity.com/paper/1606.07487/) (2016)
- [Super Mario as a String: Platformer Level Generation Via LSTMs](https://mlsanity.com/paper/1603.00930/) (2016)
- [Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencoder](https://mlsanity.com/paper/2102.12463/) (2021)
- [Conditional Level Generation and Game Blending](https://mlsanity.com/paper/2010.07735/) (2020)
- [DOOM Level Generation using Generative Adversarial Networks](https://mlsanity.com/paper/1804.09154/) (2018)
- [Dungeon and Platformer Level Blending and Generation using Conditional VAEs](https://mlsanity.com/paper/2106.12692/) (2021)
- [Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levels](https://mlsanity.com/paper/2204.06934/) (2022)

## Built on by (most cited first, 30 of 64)

- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [Evolutionary Computation in the Era of Large Language Model: Survey and Roadmap](https://mlsanity.com/paper/2401.10034/) (2024)
- [EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents](https://mlsanity.com/paper/2403.12014/) (2024)
- [GameGPT: Multi-agent Collaborative Framework for Game Development](https://mlsanity.com/paper/2310.08067/) (2023)
- [Evolving Code with A Large Language Model](https://mlsanity.com/paper/2401.07102/) (2024)
- [GameDevBench: Evaluating Agentic Capabilities Through Game Development](https://mlsanity.com/paper/2602.11103/) (2026)
- [Game Generation via Large Language Models](https://mlsanity.com/paper/2404.08706/) (2024)
- [DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback](https://mlsanity.com/paper/2410.06215/) (2024)
- [The Price of Prompting: Profiling Energy Use in Large Language Models Inference](https://mlsanity.com/paper/2407.16893/) (2024)
- [A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges](https://mlsanity.com/paper/2403.10249/) (2024)
- [Practical PCG Through Large Language Models](https://mlsanity.com/paper/2305.18243/) (2023)
- [When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challenges](https://mlsanity.com/paper/2401.10510/) (2024)
- [MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines](https://mlsanity.com/paper/2603.06679/) (2026)
- [Games for Artificial Intelligence Research: A Review and Perspectives](https://mlsanity.com/paper/2304.13269/) (2023)
- [Unbounded: A Generative Infinite Game of Character Life Simulation](https://mlsanity.com/paper/2410.18975/) (2024)
- [FactorSim: Generative Simulation via Factorized Representation](https://mlsanity.com/paper/2409.17652/) (2024)
- [DreamGarden: A Designer Assistant for Growing Games from a Single Prompt](https://mlsanity.com/paper/2410.01791/) (2024)
- [Missed Connections: Lateral Thinking Puzzles for Large Language Models](https://mlsanity.com/paper/2404.11730/) (2024)
- [ChatGPT4PCG Competition: Character-like Level Generation for Science Birds](https://mlsanity.com/paper/2303.15662/) (2023)
- [From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models](https://mlsanity.com/paper/2407.09502/) (2024)
- [GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps](https://mlsanity.com/paper/2410.07765/) (2024)
- [Grammar-based Game Description Generation using Large Language Models](https://mlsanity.com/paper/2407.17404/) (2024)
- [AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction](https://mlsanity.com/paper/2504.01014/) (2025)
- [Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection](https://mlsanity.com/paper/2602.07892/) (2026)
- [JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines](https://mlsanity.com/paper/2606.19830/) (2026)
- [Measuring Diversity of Game Scenarios](https://mlsanity.com/paper/2404.15192/) (2024)
- [ChatPCG: Large Language Model-Driven Reward Design for Procedural Content Generation](https://mlsanity.com/paper/2406.11875/) (2024)
- [Model as a Game: On Numerical and Spatial Consistency for Generative Games](https://mlsanity.com/paper/2503.21172/) (2025)
- [Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making](https://mlsanity.com/paper/2506.12012/) (2025)

## Abstract (arXiv)

Procedural Content Generation (PCG) is a technique to generate complex and diverse environments in an automated way. However, while generating content with PCG methods is often straightforward, generating meaningful content that reflects specific intentions and constraints remains challenging. Furthermore, many PCG algorithms lack the ability to generate content in an open-ended manner. Recently, Large Language Models (LLMs) have shown to be incredibly effective in many diverse domains. These trained LLMs can be fine-tuned, re-using information and accelerating training for new tasks. Here, we introduce MarioGPT, a fine-tuned GPT2 model trained to generate tile-based game levels, in our case Super Mario Bros levels. MarioGPT can not only generate diverse levels, but can be text-prompted for controllable level generation, addressing one of the key challenges of current PCG techniques. As far as we know, MarioGPT is the first text-to-level model and combined with novelty search it enables the generation of diverse levels with varying play-style dynamics (i.e. player paths) and the open-ended discovery of an increasingly diverse range of content. Code available at https://github.com/shyamsn97/mario-gpt.