Spatial Reasoning under Training and Deployment Dynamics Shift

Authors

  • Logan Webb Author
  • Paul Jenkins Author
  • Kyle Thompson Author

Abstract

Spatial attention and dual-robust offline learning require evidence at different levels. Evaluation should independently check perceptual relations and shifted transitions, then examine their combination in the chosen action. A robust value score cannot verify grounding, and a correct spatial answer cannot establish policy reliability under a transition mechanism absent from its test. This focused synthesis develops an empirical comparison that preserves the terminal action, observation process, and total verification cost. Its proposed tests are prospective; no new simulation run, model-training result, or intervention effect is reported.

References

  1. Z. Qiao, R. Yang, J. Lyu, X. Li, Z. Dai, Z. Yang, S. Gao, and S. Qiu, “Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts,” Proceedings of the 2026 International Conference on Learning Representations, 2026.
  2. S. Chen, T. Zhu, R. Zhou, J. Zhang, S. Gao, J. Niebles, M. Geva, J. He, J. Wu, and M. Li, “Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas,” Proceedings of the 42nd International Conference on Machine Learning, 2025.
  3. Zhou, Yongxi, Junwei Yao, Yuanzhe Liu, Zihan Dong, Wenbo Ye, Jiaxi Wen, and Lai Yun Choi. “Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity.” arXiv, 2026, arXiv:2608.02665. https://arxiv.org/abs/2608.02665.
  4. Tan, Wei, Yuanhao Li, and Wenkai Liang. “Evo-CuRL: Curriculum-Aware Reinforcement Learning over Code Lineage Graphs for Software Engineering Reasoning.” Proceedings of the 2026 International Conference on Multimedia Retrieval, ACM, 2026, pp. 1327-1335. https://doi.org/10.1145/3805622.3810701.
  5. Kumar, Aviral, Aurick Zhou, George Tucker, and Sergey Levine. “Conservative Q-Learning for Offline Reinforcement Learning.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 1179–1191. https://arxiv.org/abs/2006.04779.
  6. Lewis, Patrick, et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459–9474. https://arxiv.org/abs/2005.11401.
  7. Geifman, Yonatan, and Ran El-Yaniv. “Selective Classification for Deep Neural Networks.” Advances in Neural Information Processing Systems, vol. 30, 2017. https://arxiv.org/abs/1705.08500.
  8. Ovadia, Yaniv, et al. “Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift.” Advances in Neural Information Processing Systems, vol. 32, 2019. https://arxiv.org/abs/1906.02530.
  9. Bertsimas, Dimitris, and Melvyn Sim. “The Price of Robustness.” Operations Research, vol. 52, no. 1, 2004, pp. 35–53. https://doi.org/10.1287/opre.1030.0065.
  10. Rasmussen, Carl Edward, and Christopher K. I. Williams. Gaussian Processes for Machine Learning. MIT Press, 2006. https://gaussianprocess.org/gpml/.
  11. Hu, Edward J., et al. “LoRA: Low-Rank Adaptation of Large Language Models.” International Conference on Learning Representations, 2022. https://openreview.net/forum?id=nZeVKeeFYf9.
  12. Guo, Chuan, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger. “On Calibration of Modern Neural Networks.” Proceedings of the 34th International Conference on Machine Learning, PMLR, vol. 70, 2017, pp. 1321–1330. https://proceedings.mlr.press/v70/guo17a.html.

Downloads

Published

2025-11-19

Versions

Issue

Vol. 1 No. 11 (2025): November 2025

Section

Articles