GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shan, Mengyi, Curless, Brian, Kemelmacher-Shlizerman, Ira, Seitz, Steve
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911100085207040
author Shan, Mengyi
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steve
author_facet Shan, Mengyi
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steve
contents We challenge text-to-image models with generating escape room puzzle images that are visually appealing, logically solid, and intellectually stimulating. While base image models struggle with spatial relationships and affordance reasoning, we propose a hierarchical multi-agent framework that decomposes this task into structured stages: functional design, symbolic scene graph reasoning, layout synthesis, and local image editing. Specialized agents collaborate through iterative feedback to ensure the scene is visually coherent and functionally solvable. Experiments show that agent collaboration improves output quality in terms of solvability, shortcut avoidance, and affordance clarity, while maintaining visual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21839
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles
Shan, Mengyi
Curless, Brian
Kemelmacher-Shlizerman, Ira
Seitz, Steve
Computer Vision and Pattern Recognition
Computation and Language
We challenge text-to-image models with generating escape room puzzle images that are visually appealing, logically solid, and intellectually stimulating. While base image models struggle with spatial relationships and affordance reasoning, we propose a hierarchical multi-agent framework that decomposes this task into structured stages: functional design, symbolic scene graph reasoning, layout synthesis, and local image editing. Specialized agents collaborate through iterative feedback to ensure the scene is visually coherent and functionally solvable. Experiments show that agent collaboration improves output quality in terms of solvability, shortcut avoidance, and affordance clarity, while maintaining visual quality.
title GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2506.21839