arXiv cs.AI· Yang Zhou, Zixuan Huang, Sunzhu Li, Zhuo Yang, Chen Zhang, Shunian Chen, Caijun Yan, Jianyao Xu, Shunyu Liu, Weijie Fu, Peiliang Li, Xiaozhi Chen, Yuxiang Cai·· 14 小时前AI 评分42
SpatialCLI：让 VLM 先借助空间工具推理，再逐步内化这些能力
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
AI 导读
SpatialCLI 框架通过“调用工具—学习使用—内化能力”三阶段，让 VLM 借助专业视觉模型作为空间工具提升感知，再将这些能力内化。在 MindCube 上，Qwen3-VL-8B-Instruct 借助工具从 29.3% 提升至 84.6%，超过同样使用工具的 GPT-5.6 Sol（72.1%），内化后无工具仍保留 73.8%。
正文 · 原文
Authors:Yang Zhou, Zixuan Huang, Sunzhu Li, Zhuo Yang, Chen Zhang, Shunian Chen, Caijun Yan, Jianyao Xu, Shunyu Liu, Weijie Fu, Peiliang Li, Xiaozhi Chen, Yuxiang Cai
Abstract:Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning. However, a fundamental capability mismatch remains: general VLMs can reason about the overall task but often miss the visual details that determine success, while specialist vision models can capture those details but cannot translate them into task-level decisions. In this work, we propose SpatialCLI, a framework that teaches VLMs to reason with spatial tools and progressively internalize the specialist perceptual capabilities they provide. SpatialCLI proceeds in three stages: (1) Call exposes specialist vision models as spatial tools to augment the VLM's perception; (2) Learn uses Cold-Start SFT and agentic RL to improve tool use; and (3) Internalize verbalizes successful tool-use trajectories to internalize specialist perceptual capabilities. We further introduce SpatialCLI-Bench, a 516-example benchmark for compositional perception across localization, segmentation, depth, and pose. On MindCube, SpatialCLI raises Qwen3-VL-8B-Instruct from 29.3% to 84.6% with tools, surpassing GPT-5.6 Sol with tools (72.1%), while retaining 73.8% without tools after internalization.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.27703 [cs.AI] |
| (or arXiv:2607.27703v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.27703 arXiv-issued DOI via DataCite |
Submission history
From: Yang Zhou [view email]
[v1]
Thu, 30 Jul 2026 05:39:01 UTC (5,347 KB)
[v2]
Tue, 4 Aug 2026 12:14:50 UTC (5,346 KB)
[v3]
Mon, 26 Oct 2026 09:20:14 UTC (5,346 KB)
来源：arXiv cs.AI · arxiv.org