mlsanityData to 7 Oct 2026

A Configurable Library for Generating and Manipulating Maze Datasets

arXiv 2309.10498 ↗First posted 19 Sep 2023cs.LG cs.AI cs.SEcited by 31

Not on the map. Why?

Cited by 23 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Understanding how machine learning models respond to distributional shifts is a key research challenge. Mazes serve as an excellent testbed due to varied generation algorithms offering a nuanced platform to simulate both subtle and pronounced distributional shifts. To enable systematic investigations of model behavior on out-of-distribution data, we present textttmaze-dataset, a comprehensive library for generating, processing, and visualizing datasets consisting of maze-solving tasks. With this library, researchers can easily create datasets, having extensive control over the generation algorithm used, the parameters fed to the algorithm of choice, and the filters that generated mazes must satisfy. Furthermore, it supports multiple output formats, including rasterized and text-based, catering to convolutional neural networks and autoregressive transformer models. These formats, along with tools for visualizing and converting between them, ensure versatility and adaptability in research applications.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 7 of its 23 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

7 of 23 references.

References · 7

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  3. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  4. 2021Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networkscited by 108
  5. 2023Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysiscited by 35
  6. 2023Evaluating ChatGPT and GPT-4 for Visual Programmingcited by 13
  7. 2021Datasets for Studying Generalization from Easy to Hard Examplescited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 12; 2026: 13.

31 papers.

Sort:

By area:

  1. 2025Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawingcited by 130
  2. 2025Visual Planning: Let's Think Only with Imagescited by 85
  3. 2025Zebra-CoT: A Dataset for Interleaved Vision Language Reasoningcited by 78
  4. 2024Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoningcited by 33
  5. 2025AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPOcited by 33
  6. 2025DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Modelscited by 18
  7. 2026Visual Generation Unlocks Human-Like Reasoning through Multimodal World Modelscited by 18
  8. 2023Structured World Representations in Maze-Solving Transformerscited by 16
  9. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  10. 2024Transformers Use Causal World Models in Maze-Solving Taskscited by 13
  11. 2024Transformers Can Navigate Mazes With Multi-Step Predictioncited by 11
  12. 2025ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representationscited by 11
19 more
  1. 2025MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluationcited by 11
  2. 2026Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoningcited by 10
  3. 2025Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalizationcited by 8
  4. 2024On Logical Extrapolation for Mazes with Recurrent and Implicit Networkscited by 7
  5. 2025Adaptive Inference-Time Scaling via Cyclic Diffusion Searchcited by 7
  6. 2025VFScale: Intrinsic Reasoning through Verifier-Free Test-time Scalable Diffusion Modelcited by 6
  7. 2025MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoningcited by 6
  8. 2026Chain of Mindset: Reasoning with Adaptive Cognitive Modescited by 2
  9. 2026Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thoughtcited by 2
  10. 2026BODHI: Do LLMs Branch Out and Discover Heterogeneous Inferences?cited by 2
  11. 2026Thinking into the Future: Latent Lookahead Training for Transformerscited by 1
  12. 2026The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Modelscited by 1
  13. 2026Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoningcited by 1
  14. 2026Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillationcited by 1
  15. 2026Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processescited by 1
  16. 2025Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learningcited by 0
  17. 2026SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimizationcited by 0
  18. 2026SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learningcited by 0
  19. 2026Resolving State-Representation Mismatch: State-Space Visual Reasoning for Open-Loop VLA Planningcited by 0