A neuro-symbolic 2.5-D decomposition lets LLMs plan in 2D while deterministic rules compute vertical placements, raising structural accuracy to 94.6% on the Build What I Mean benchmark.
Nemotron-3-Super-120B-A12B
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
2.5-D Decomposition for LLM-Based Spatial Construction
A neuro-symbolic 2.5-D decomposition lets LLMs plan in 2D while deterministic rules compute vertical placements, raising structural accuracy to 94.6% on the Build What I Mean benchmark.