SOURCE-LINKED INTELLIGENCE

CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs). However, these methods typically rely on repeated generation or external verification. To address this limitation, we introduce CritICL, a novel inference-time framework that improves reasoning while maintaining high efficiency. Our key insight is that LLM failure modes exhibit structured patterns across model scales within the same family. Instead of treating failures as undesirable outputs, CritICL leverages them as a source of guidance. Specifically, we utilize fa

Read original source ↗ Open in workspace

recordType

paper

region

Global