跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-21AI 評分34

SpatialBrain:透過經驗提升空間推理能力

SpatialBrain: Spatial Intelligence Growing from Experience

AI 導讀

SpatialBrain 是一套提升空間推理能力的框架,透過區分場景證據與推理經驗,在固定視覺語言主幹模型的前提下引導工具使用。框架整合空間記憶、可重用的技能程序及經整理的流程記錄,累積和運用過往經驗。在五項空間推理基準測試中,SpatialBrain 在四項優於同一主幹模型直接作答,另一項則表現相同。

正文

Published on Oct 21

Authors:

,

,

,

,

,

,

Abstract

SpatialBrain improves spatial reasoning by separating scene evidence from reasoning experience, using fused spatial memory, reusable skill procedures, and consolidated process records to guide tool use without altering the vision-language backbone.

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.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2610.29317

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.29317 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.29317 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.29317 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co