Immediate Inference: The Missing Foundation in Large Language Model Logical Reasoning

While extensive research has evaluated LLMs on complex reasoning tasks, the foundational building blocks of logical reasoning remain un-derexplored. We introduce IIBench , a benchmark evaluating immediate inference (elementary operations over categorical propositions). Our evaluation reveals that even SoTA models exhibit systematic deficiencies in immediate inference, and establishes immediate inference as foundational: it mediates approximately 40% of the effect on syllogistic reasoning, with near-perfect correlation ( ρ = 0.98) across reasoning benchmarks. Our analysis reveals that models lack robust operator grounding, oscillating be-tween structural reasoning and surface pattern matching with inconsistent handling of quantifiers and negation. 1