# SpatialClaw：重新思考智能体空间推理的动作接口

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-11 08:00
- AIHOT 分数：58
- AIHOT 链接：https://aihot.virxact.com/items/cmqac9xug0k4zslldz34mgn2q
- 原文链接：https://arxiv.org/abs/2606.13673

## AI 摘要

SpatialClaw 是无需训练的空间推理框架，采用代码作为动作接口，维护预加载输入帧和感知几何原语的状态化 Python 内核，让 VLM 驱动的智能体逐步编写可执行代码单元，灵活组合分析感知结果。在 20 个静态和动态 3D/4D 空间推理基准上平均准确率达 59.9%，比近期空间智能体提升 11.2 个百分点，且在不做基准或模型适配的情况下，在六个 VLM 骨干上均取得一致提升。

## 正文

Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-augmented agents attempt to address this by augmenting VLMs with specialist perception modules, yet their effectiveness is bounded by the action interface through which those tools are invoked. In this work, we study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning. Existing spatial agents either employ single-pass code execution, which commits to a full analysis strategy before any intermediate result is observed, or rely on a structured tool-call interface that often offers less flexibility for freely composing operations or tailoring the analysis to each task. Both designs offer limited flexibility for open-ended, complex 3D/4D spatial reasoning. We therefore propose SpatialClaw, a training-free framework for spatial reasoning that adopts code as the action interface. SpatialClaw maintains a stateful Python kernel pre-loaded with input frames and a suite of perception and geometry primitives, letting a VLM-backed agent write one executable cell per step conditioned on all prior outputs, enabling the agent to flexibly compose and manipulate perception results and adapt its analysis to both intermediate text and visual observations and the demands of each problem. Evaluated across 20 spatial reasoning benchmarks spanning a broad range of static and dynamic 3D/4D spatial reasoning tasks, SpatialClaw achieves 59.9% average accuracy, outperforming the recent spatial agent by +11.2 points, with consistent gains across six VLM backbones from two model families without any benchmark- or model-specific adaptation.