Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time

📰 ArXiv cs.AI

arXiv:2504.12329v2 Announce Type: replace-cross Abstract: Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free framework that enables large reasoning models to guide smaller ones during inference at the reasoning level, distinct from speculative decoding, which operates at the token level. Our approach is based

Published 4 Jun 2026

Full Article

Title: Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time

Abstract:
arXiv:2504.12329v2 Announce Type: replace-cross Abstract: Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free framework that enables large reasoning models to guide smaller ones during inference at the reasoning level, distinct from speculative decoding, which operates at the token level. Our approach is based
Read full paper → ← Back to Reads