SpatialCLI shows that a VLM can learn to use localization, segmentation, depth, and pose tools and then internalize the tool outputs into direct reasoning, improving both tool-enabled and tool-free spatial task performance.
Since 0.776 < 0.928, the **blue receptacle is closer**
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
SpatialCLI shows that a VLM can learn to use localization, segmentation, depth, and pose tools and then internalize the tool outputs into direct reasoning, improving both tool-enabled and tool-free spatial task performance.