mlsanityData to 7 Oct 2026

GenEscape: Hierarchical Multi-Agent Generation of Escape Room Puzzles

arXiv 2506.21839 ↗First posted 27 Jun 2025cs.CV cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 61 references that are in the map. First posted on arXiv 27 Jun 2025.

Builds on

23 of 61 references.

References · 23

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  5. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  6. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  7. 2024Long-CLIP: Unlocking the Long-Text Capability of CLIPcited by 298
  8. 2024Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understandingcited by 294
  9. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  10. 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 246
  11. 2022Optimizing Prompts for Text-to-Image Generationcited by 204
  12. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
11 more
  1. 2024GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editingcited by 132
  2. 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesiscited by 123
  3. 2024PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patternscited by 54
  4. 2024Dynamic Prompt Optimizing for Text-to-Image Generationcited by 45
  5. 2024Universal Prompt Optimizer for Safe Text-to-Image Generationcited by 27
  6. 2024Planning with Multi-Constraints via Collaborative Language Agentscited by 26
  7. 2025MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audiocited by 24
  8. 2025MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generationcited by 23
  9. 2024LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Executioncited by 20
  10. 2024PUZZLES: A Benchmark for Neural Algorithmic Reasoningcited by 12
  11. 2021Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networkscited by 7

Built on by

Not cited yet.