CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations
Abstract
Large Language Model (LLM) agents, while proficient in the digital realm, face a significant gap in physical-world deployment due to the challenge of forming and maintaining a robust spatial mental model. We identify three core cognitive challenges hindering this transition: spatial reasoning, long-horizon state tracking via mental simulation, and active exploration under partial observation. To isolate and evaluate these faculties, we introduce CubeBench, a novel generative benchmark centered on the Rubik's Cube. CubeBench uses a three-tiered diagnostic framework that progressively assesses agent capabilities, from foundational state tracking with full symbolic information to active exploration with only partial visual data. Our experiments on leading LLMs reveal critical limitations, including a uniform 0.00% pass rate on all long-horizon tasks, exposing a fundamental failure in long-term planning. We also propose a diagnostic framework to isolate these cognitive bottlenecks by providing external solver tools. By analyzing the failure modes, we provide key insights to guide the development of more physically-grounded intelligent agents.
Links & Resources
Authors
Cite This Paper
Gao, H., Zhang, Z., Luo, T., Yang, K., Juan, X., Qiu, J., Chen, T., He, B., Zhao, H., Zhou, H., Liu, S., Wang, M. (2025). CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations. arXiv preprint arXiv:2512.23328.
Huan-ang Gao, Zikang Zhang, Tianwei Luo, Kaisen Yang, Xinzhe Juan, Jiahao Qiu, Tianxing Chen, Bingxiang He, Hao Zhao, Hao Zhou, Shilong Liu, and Mengdi Wang. "CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations." arXiv preprint arXiv:2512.23328 (2025).