NeurIPS 2025poster0 citations
Knot So Simple: A Minimalistic Environment for Spatial Reasoning
Abstract
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.
spatial reasoningreinforcement learningvisual reasoning
BibTeX
@inproceedings{
chen2025knot,
title={Knot So Simple: A Minimalistic Environment for Spatial Reasoning},
author={Zizhao Chen and Yoav Artzi},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2025},
url={https://openreview.net/forum?id=M15Fnbh3pa}
}