Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by letting the model actively gather evidence with 3D perception tools instead of answering in a single pass.
ORIGINAL PAPER
S-Agent 2.0: Spatial Reasoning with a General Coding Agent
WHAT WE KNOW
Even so, on many questions the tools return the right evidence and the model still does not arrive at the correct answer: the gap between model and tools, where raw readings become usable conclusions, is left unfilled. We present S-Agent 2.
WATCH NEXT
Review the primary source, validate the main result, and establish whether any listed-company transmission is direct.
EVIDENCE
What the evidence supports so far
Research signals
agent
multimodal
reasoning
What remains unverified
The full methodology, effect size, and limitations still require analyst review.
Company impact remains unverified until a direct economic transmission is established.