HuggingFace Daily Papers·· 1 天前
SpatialBrain：从经验中生长的空间智能
SpatialBrain: Spatial Intelligence Growing from Experience
AI 导读
SpatialBrain 框架在保持视觉语言主干模型固定的前提下，让推理器积累“何时直接观察、何时重建或测量”的经验。其 3DFusionMemory 将当前场景观测融合为可查询的空间关系，Spatial Skill Library 提供可复用工具流程，Spatial Cognition 则将任务条件与经验关联。
正文 · 原文
Abstract:Spatial reasoning requires more than access to geometric tools: a reasoner must decide when direct observation is sufficient and when to reconstruct, measure, or change reference frames. We present SpatialBrain, a framework that retains experience about these decisions while keeping its vision-language backbone fixed. The key distinction is between evidence about a scene and experience about how to reason with that evidence. 3DFusionMemory fuses current-scene observations into queryable spatial relations. A Spatial Skill Library provides reusable tool procedures, and Spatial Cognition associates task conditions with experience about when and how to use memory and skills. Completed trajectories are abstracted into process records and consolidated between task blocks, allowing later decisions to draw on earlier execution without transferring scene coordinates or reference answers. Across five spatial-reasoning benchmarks, SpatialBrain improves on direct answers from the same backbone on four and ties on the fifth. Component comparisons, experience-coverage curves, and traced resource decisions characterize how the framework accumulates and uses these resources.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29317 [cs.AI] |
| (or arXiv:2610.29317v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29317 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yifan Zhou [view email]
[v1]
Wed, 21 Oct 2026 07:15:54 UTC (7,713 KB)
来源：HuggingFace Daily Papers · arxiv.org