Introduces a logic puzzle benchmark, a pipeline to build verifiable reasoning graphs from traces, and a concentration-based efficiency metric to distinguish model reasoning behaviors.
Title resolution pending
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
-
Reasoning Structure of Large Language Models
Introduces a logic puzzle benchmark, a pipeline to build verifiable reasoning graphs from traces, and a concentration-based efficiency metric to distinguish model reasoning behaviors.