Procedural Content Generation

Ask about this topic

Overview

Procedural content generation studies how to create digital content automatically, from playable levels and maps to 3D worlds, characters, materials, and narratives. Approaches include rule- and constraint-based systems, search and evolutionary methods, reinforcement learning, and generative models such as diffusion models and large language models, often combined in agent workflows. These techniques can make content more varied and easier to adapt, while supporting synthetic data and reproducible environments for games, robotics, and agent training. A central challenge is balancing diversity and visual or narrative quality with controllability, playability, structural consistency, and reliable evaluation.

Latest papers

CardsList

67 papers8 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. Syntactic Segmentation and Collage Generation for Videogame Levels with Perceptual Distance

    Oct 28, 2026Ross Mawhorter, Matthew GuzdialProcedural Content Generation

    University of Alberta 116 Street and 85th Avenue Edmonton, AB T6G 2R3

  2. InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation

    Oct 19, 2026Yi-Chuan Huang, Hao-Jen Chien, Zheng-Hui Huang +3Procedural 3D Generation3D Scene Generation

    Alaya Lab · National Yang Ming Chiao Tung University · National Taiwan University

  3. CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games

    Oct 15, 2026Gaëtan Berlaimont, Justin Vanwichelen, Benoît Ronval +1Large Language Model-Based Role-Play SimulationProcedural Content Generation

    UCLouvain, Louvain-la-Neuve, Belgium

  4. Dungeon and Visibility World Generator

    Oct 14, 2026Edwin Mériaux, Antonio Loría, Gregory DudekProcedural Content Generation

    McGill University, Montréal QC H3A 0G4, Canada · Université Paris-Saclay, 91190 Gif-sur-Yvette, France · CNRS, Laboratoire des Signaux et Systèmes (L2S), 91190 Gif-sur-Yvette, France

  5. CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations

    Oct 13, 2026Jiahui Sun, Ran Bi, Yifei Liu +8Aerial 3D Reconstruction3D Scene Representation

    Nanjing University · Shanghai Artificial Intelligence Laboratory · Beihang University +3

  6. WorldBench: Evaluating LLMs on Three.js Voxel World Generation

    Oct 7, 2026Krish BakshiLLM Code Generation3D Scene Generation

  7. Code2Games: Enabling Coding Agents for Gaming World Generation

    Oct 4, 2026Wei Wu, Ziyang Xu, Zeyu Zhang +2Agentic Code Generation3D Scene Generation

    School of Computer Science, Peking University · La Trobe University

  8. A Vision-Language Model (VLM)-based Pipeline for End-to-End Procedural Modeling of Field-Grown Maize from Point Clouds

    Oct 2, 2026Mozhgan Hadadi, Talukder Z. Jubery, Adarsh Krishnamurthy +1Procedural 3D Generation3D Reconstruction

  9. WorldWeave: Growing Persistent Geometric Worlds for Video Generation

    Sep 28, 2026Yifan Huang, Lifan Jiang, Qingyue Hao +5Memory-Augmented Video Generation3D Scene Generation

    Zhejiang University · Daerwen AI

  10. CompoWorld: Compositional Environment Scaling for General Agents

    Sep 27, 2026Xiao-Wen Yang, Weiyi Xu, Wen Da +9Tool-Augmented Language Model AgentsTool-Using Agents

    AllSpark Team

  11. PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation

    Sep 22, 2026Maan Qraitem, Kate Saenko, Bryan A. PlummerPersonality Modeling in Language ModelsProcedural Content Generation

    Boston University

  12. ProxyBuild: Text-Guided Structured 3D Building Generation with Mesh-Anchored Procedural Proxies

    Sep 20, 2026Xiang Tang, Ruotong Li, Xiaopeng Fan3D Asset Generation3D Scene Generation

    Harbin Institute of Technology, Shenzhen · Pengcheng Laboratory · Harbin Institute of Technology +1

  13. AquaWorld: Structure-Consistent Underwater World Generation for Robot Simulation

    Sep 19, 2026Bin Peng, Tiandong Zhang, Ruidong Wang +2Robotics SimulationSynthetic Data Generation for Robotics

    State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Ocean College, Zhejiang University, Zhejiang, China

  14. Coastal Environment Generation with HoloOcean

    Sep 9, 2026Abigail Austin, Brady Moon, Joshua G. MangelsonRobotics Simulation3D Scene Generation

    Brigham Young University

  15. Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Exploration

    Sep 8, 2026Yiran Qiao, Feng Wang, Jing MaWorld Model-Based PlanningAction-Conditioned World Models

    Case Western Reserve University · Johns Hopkins University

  16. Programmable Cellular Automata

    Sep 5, 2026Ahmed Khalifa, Muhammad Umair Nasir, Matthew Siper +2Cellular AutomataGenerative Modeling

    Institute of Digital Games, University of Malta, 20 L. Esperanto, L-Imsida, Malta · Nof1, 665 Broadway, Brooklyn, NY 10012, USA · University of the Witwatersrand, 1 Jan Smuts Ave, Braamfontein, Johannesburg, 2017, South Africa +1

  17. CogEvol: Towards Efficient and Reliable Learning Environment Generation

    Aug 31, 2026Shangqing Tu, Daniel Zhang-Li, Yucheng Wang +20Generative AI in EducationProcedural Content Generation

    CogEvol Inc. & Tsinghua University

  18. 4DSynth: Controllable Procedural World Synthesis for Dynamic Embodied Simulation

    Aug 27, 2026Zehao Qi, Haochen Luo, Jia-Wang Bian +2Procedural Content Generation4D Scene Generation

    Nanyang Technological University, Singapore · University of Oxford, UK · Princeton University, USA +1

  19. OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games

    Aug 27, 2026Jiang JunProcedural Content Generation

  20. Growing a Stand, Not a Tree: Joint Canopy Generation Reproduces Crown Shyness

    Aug 27, 2026Guang Yang, Fengchen LiuGenerative ModelingProcedural Content Generation

    Phi Lab Foundation · University of California, Berkeley

  21. Procedura: Agentic 3D Modeling with Procedural Control

    Aug 26, 2026Youtian Lin, Yikang Yang, Zhanpeng Hu +5Procedural 3D GenerationText-to-3D Generation

    Nanjing University · Envision

  22. RoboRacer Arena: Specification-Driven Track Construction for Autonomous Racing

    Aug 24, 2026Mihaela-Larisa Clement, Agnes Poks, Ezio BartocciAutonomous RacingProcedural Content Generation

    1TU Wien, Vienna, Austria. · 2AIT Austrian Institute of Technology, Vienna, Austria.

  23. EnvHarness: Awakening Static Worlds for Agent Learning

    Aug 20, 2026Chengsong Huang, Zifeng Wang, Rujun Han +14LLM Agent HarnessesAgent Harness Optimization

    Washington University in St. Louis · Google Cloud AI Research · University of North Carolina at Chapel Hill +1

  24. aDSL: Agentic 3D Creation via Joint Agent-Program Design

    Aug 18, 2026Rui-Huan Wang, Si-Tong Wei, Jia-Qi He +3LLM-Based Program SynthesisText-to-3D Generation

    Peking University, China

  25. Procedural Content Metageneration via Program Search and Continual Abstraction Discovery

    Aug 18, 2026Matthew Siper, Ahmed Khalifa, Julian TogeliusProcedural Content GenerationProgram Synthesis

    Game Innovation Lab New York University New York, USA · Institute of Digital Games University of Malta Msida, Malta

  26. Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior

    Aug 17, 2026Yifan Lu, Xiaopeng Yuan, Haohan WangUser ModelingPersonality Modeling in Language Models

    Imperial College London · University of Illinois Urbana-Champaign

  27. Solvable Sokoban Without a Solver via Diffusion

    Aug 16, 2026Sina BaghalProcedural Content GenerationDiffusion Models

  28. RoadWeaver: Large-Scale Lane-Level HD Map Generation from Scratch for Autonomous Driving Simulation

    Aug 12, 2026Yueyuan Li, Zexi Chen, Weijie Xi +4HD Map ConstructionProcedural Content Generation

  29. WorldClaw: Agentic 3D Open-World Generation at Scale

    Aug 5, 2026Chunchao Guo, Jinpeng Li, Yang Li +1Open-Ended Generation3D Asset Generation

    Tencent Hunyuan

  30. GS-Agent: Creating 4D Physical Worlds With Generative Simulation

    Jul 23, 2026Hongxin Zhang, Chunru Lin, Junyan Li +3Procedural Content Generation4D Scene Generation

    University of Massachusetts Amherst · Genesis AI