New "Cake" Representation Enhances Dynamic Game Level Generation

Emily Halina, Matthew Guzdial· July 15, 2026 View original

Summary

Researchers introduce a novel "cake" representation for video game levels that implicitly encodes dynamic information over time. Their new generation approach, Playtrace Reconstructive Partitioning (PRP), creates valid and diverse levels, outperforming existing methods in games like Sokoban.

This paper proposes a new method for procedural content generation (PCG) in video games, focusing on the dynamic nature of game levels. Traditional PCG often abstracts away the temporal element, but this research introduces a "cake" representation that inherently captures how levels evolve during gameplay. To leverage this new representation, the authors developed Playtrace Reconstructive Partitioning (PRP), a domain-independent algorithm designed to generate levels using the "cake" structure. Evaluations against six state-of-the-art PCG techniques in the game Sokoban demonstrated that PRP successfully generates valid levels while maintaining solution diversity, suggesting a more effective way to handle the implicit dynamics of game design.

Why it matters

Game developers and AI researchers can leverage this novel representation and generation technique to create more dynamic, engaging, and diverse game content efficiently.

How to implement this in your domain

  1. 1Explore the "cake" representation for designing game levels that evolve over time.
  2. 2Integrate Playtrace Reconstructive Partitioning (PRP) into existing game engines for automated level design.
  3. 3Experiment with PRP in different game genres beyond puzzle games to assess its versatility.
  4. 4Develop tools to visualize and edit levels created using the "cake" representation and PRP.

Who benefits

GamingEntertainmentEdTechSimulation

Key takeaways

  • A new "cake" representation captures the dynamic, temporal nature of game levels.
  • Playtrace Reconstructive Partitioning (PRP) is a novel algorithm for generating levels with this representation.
  • PRP generates valid and diverse levels, outperforming several existing PCG methods.
  • The approach offers a domain-independent way to create dynamic game content.

Original post by Emily Halina, Matthew Guzdial

"arXiv:2607.12097v1 Announce Type: new Abstract: Video games are a dynamic medium experienced over time. While there are many Procedural Content Generation (PCG) approaches for generating video game levels, they often use representations that abstract away this dynamic nature. In…"

View on X

Originally posted by Emily Halina, Matthew Guzdial on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses