LLMs solve routine arithmetic and primality checks well but consistently fail at the Game of 24, which requires trial-and-error search.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Fragile Number Sense: Probing the Elemental Limits of Numerical Reasoning in LLMs
LLMs solve routine arithmetic and primality checks well but consistently fail at the Game of 24, which requires trial-and-error search.