Knot So Simple: A Minimalistic Environment for Spatial Reasoning

We propose KnotGym, an interactive environment for complex, spatial reasoning and manipulation. KnotGym includes goal-oriented rope manipulation tasks with varying levels of complexity, all requiring acting from pure image observations. Tasks are defined along a clear and quantifiable axis of complexity based on the number of knot crossings, creating a natural generalization test. KnotGym has a simple observation space, allowing for scalable development, yet it highlights core challenges in integrating acute perception, spatial reasoning, and grounded manipulation. We evaluate methods of different classes, including model-based RL, model-predictive control, and chain-of-thought reasoning, and illustrate the challenges KnotGym presents. KnotGym is available atthis https URL.

@article{chen2025_2505.18028,
  title={ Knot So Simple: A Minimalistic Environment for Spatial Reasoning },
  author={ Zizhao Chen and Yoav Artzi },
  journal={arXiv preprint arXiv:2505.18028},
  year={ 2025 }
}