Tag
Introduces a novel 'cake' representation for game levels over time that implicitly encodes dynamic information, along with a generative approach (Playtrace Reconstructive Partitioning, PRP) that outperforms six state-of-the-art PCG methods in Sokoban by producing valid levels without sacrificing solution diversity.
A benchmark tests LLMs on strict Sokoban puzzles with formatting constraints, finding only ChatGPT, Qwen3.7-max, and Gemini 3.5-thinking succeed, while others fail due to illegal moves or formatting errors.