mlsanityData to 14 Oct 2026

MarioGPT: Open-Ended Text2Level Generation through Large Language Models

arXiv 2302.05981 ↗First posted 12 Feb 2023cs.AI cs.CL cs.LGcited by 64

Not on the map. Why?

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.

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

32 of 52 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  8. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  9. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  10. 2019How Can We Know What Language Models Know?cited by 959
  11. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  12. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
20 more
  1. 2015Illuminating search spaces by mapping elitescited by 425
  2. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  3. 2022Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Modelscited by 220
  4. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 137
  5. 2022Evolution through Large Modelscited by 134
  6. 2019Covariance Matrix Adaptation for the Rapid Illumination of Behavior Spacecited by 78
  7. 2018Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Networkcited by 76
  8. 2020Deep Learning for Procedural Content Generationcited by 73
  9. 2023Level Generation Through Large Language Modelscited by 68
  10. 2019Increasing Generality in Machine Learning through Procedural Content Generationcited by 59
  11. 2020Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Networkcited by 52
  12. 2016The VGLC: The Video Game Level Corpuscited by 41
  13. 2016Super Mario as a String: Platformer Level Generation Via LSTMscited by 40
  14. 2021Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencodercited by 27
  15. 2020Conditional Level Generation and Game Blendingcited by 17
  16. 2018DOOM Level Generation using Generative Adversarial Networkscited by 15
  17. 2021Dungeon and Platformer Level Blending and Generation using Conditional VAEscited by 10
  18. 2022Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levelscited by 8
  19. 2022Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometrycited by 5
  20. 2021Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021cited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 26; 2025: 19; 2026: 14.

64 papers.

Sort:

By area:

  1. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  2. 2024Large Language Models and Games: A Survey and Roadmapcited by 93
  3. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 90
  4. 2024EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agentscited by 46
  5. 2023GameGPT: Multi-agent Collaborative Framework for Game Developmentcited by 43
  6. 2024Evolving Code with A Large Language Modelcited by 43
  7. 2026GameDevBench: Evaluating Agentic Capabilities Through Game Developmentcited by 28
  8. 2024Game Generation via Large Language Modelscited by 25
  9. 2024DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedbackcited by 25
  10. 2024The Price of Prompting: Profiling Energy Use in Large Language Models Inferencecited by 23
  11. 2024A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challengescited by 22
  12. 2023Practical PCG Through Large Language Modelscited by 21
38 more
  1. 2024When Large Language Models Meet Evolutionary Algorithms: Potential Enhancements and Challengescited by 20
  2. 2026MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Enginescited by 16
  3. 2023Games for Artificial Intelligence Research: A Review and Perspectivescited by 14
  4. 2024Unbounded: A Generative Infinite Game of Character Life Simulationcited by 14
  5. 2024FactorSim: Generative Simulation via Factorized Representationcited by 10
  6. 2024DreamGarden: A Designer Assistant for Growing Games from a Single Promptcited by 10
  7. 2024Missed Connections: Lateral Thinking Puzzles for Large Language Modelscited by 9
  8. 2023ChatGPT4PCG Competition: Character-like Level Generation for Science Birdscited by 8
  9. 2024From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Modelscited by 8
  10. 2024GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Mapscited by 8
  11. 2024Grammar-based Game Description Generation using Large Language Modelscited by 7
  12. 2025AnimeGamer: Infinite Anime Life Simulation with Next Game State Predictioncited by 7
  13. 2026Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projectioncited by 6
  14. 2026JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Enginescited by 6
  15. 2024Measuring Diversity of Game Scenarioscited by 5
  16. 2024ChatPCG: Large Language Model-Driven Reward Design for Procedural Content Generationcited by 5
  17. 2025Model as a Game: On Numerical and Spatial Consistency for Generative Gamescited by 5
  18. 2025Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Makingcited by 5
  19. 2024SCAPE: Searching Conceptual Architecture Prompts using Evolutioncited by 4
  20. 2024G-PCGRL: Procedural Graph Data Generation via Reinforcement Learningcited by 4
  21. 202590% Faster, 100% Code-Free: MLLM-Driven Zero-Code 3D Game Developmentcited by 4
  22. 2026Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Ratecited by 4
  23. 2024Generative Design through Quality-Diversity Data Synthesis and Language Modelscited by 3
  24. 20243D Building Generation in Minecraft via Large Language Modelscited by 3
  25. 2025Can Large Language Models Capture Video Game Engagement?cited by 3
  26. 2025PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learningcited by 3
  27. 2025Word2Minecraft: Generating 3D Game Levels through Large Language Modelscited by 3
  28. 2025Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RLcited by 3
  29. 2026AI for Games in the Foundation Model Eracited by 3
  30. 2023Learning Curricula in Open-Ended Worldscited by 2
  31. 2024Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learningcited by 2
  32. 2025Grammar and Gameplay-aligned RL for Game Description Generation with LLMscited by 2
  33. 2025UniCAIM: A Unified CAM/CIM Architecture with Static-Dynamic KV Cache Pruning for Efficient Long-Context LLM Inferencecited by 2
  34. 2025ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Searchcited by 2
  35. 2025Boardwalk: Towards a Framework for Creating Board Games with LLMscited by 2
  36. 2025Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Modelscited by 1
  37. 2025Rule Synergy Analysis using LLMs: State of the Art and Implicationscited by 1
  38. 2025Mortar: Evolving Mechanics for Automatic Game Designcited by 1

50 most cited of 64 All 64 (JSON)