arXiv：cs.AI· Junlin Wu, Wen Fan, Dandan Zhang·· 6 小时前
世界模型中面向可靠短程规划的序一致潜在几何
Order-Consistent Latent Geometry for Reliable Short-Horizon Planning in World Models
AI 导读
研究指出，用终端欧氏距离对候选动作序列排序的潜在规划器，其路径无逆转要求正是经典的自接近（self-approaching）条件，违反该条件会导致有限时域内候选顺序精确反转。
正文
Abstract:Latent planners often rank candidate action sequences by terminal Euclidean distance to a goal latent. Exact agreement with transition distance would make this score ideal, but is stronger than planning requires: along a transition-shortest rollout, the essential requirement is that latent distance does not reverse true transition progress. We show that this pathwise no-reversal requirement is precisely the classical self-approaching condition. To the best of our knowledge, we are the first to identify self-approachingness as a planner-facing compatibility condition for terminal Euclidean latent planning and to connect its violation to an exact finite-horizon candidate-order reversal. Because visual world models predict discrete latent sequences, we analyze their polygonal interpolation. We prove that an acute bend creates a nonempty region in which terminal Euclidean distance ranks a transition-worse candidate ahead of one that makes genuine progress, even under exact rollouts. We further interpret latent dimension as angular capacity through a classical spherical-code bound. A controlled six-branch experiment, including a zero-padded three-dimensional baseline, validates the predicted ordering failure and separates angular arrangement from ambient dimensionality.
| Comments: | Accepted for poster presentation at STEAI 2026 (ECCV 2026 Workshop) |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18570 [cs.AI] |
| (or arXiv:2610.18570v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18570 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junlin Wu [view email]
[v1]
Tue, 13 Oct 2026 15:38:45 UTC (43 KB)
来源：arXiv：cs.AI · arxiv.org