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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Wang, Yue, Xiang, Chaudhary, Vipin, Han, Xiaotian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909582071169024
author Yang, Wang
Yue, Xiang
Chaudhary, Vipin
Han, Xiaotian
author_facet Yang, Wang
Yue, Xiang
Chaudhary, Vipin
Han, Xiaotian
contents 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 on two observations: (1) reasoning-supportive tokens such as "wait" frequently appear after structural delimiters like "\n\n", serving as signals for reflection or continuation; and (2) larger models exhibit stronger control over reflective behavior, reducing unnecessary backtracking while improving reasoning quality. By strategically delegating reflective steps to a more capable model, our method significantly boosts the reasoning accuracy of reasoning models while shortening their output. With the assistance of the 32B reasoning model, the 1.5B model's accuracy on MATH500 increases from 83.2% to 89.4%, marking a substantial improvement of 6.2%. Simultaneously, the average output length is reduced from 5439 tokens to 4583 tokens, representing a 15.7% decrease. Moreover, when applied to a non-reasoning model (Qwen-2.5-7B-Instruct), our framework boosts its accuracy from 74.0% to 81.8% on the same benchmark, achieving a relative improvement of 7.8%.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12329
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
Yang, Wang
Yue, Xiang
Chaudhary, Vipin
Han, Xiaotian
Computation and Language
Artificial Intelligence
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 on two observations: (1) reasoning-supportive tokens such as "wait" frequently appear after structural delimiters like "\n\n", serving as signals for reflection or continuation; and (2) larger models exhibit stronger control over reflective behavior, reducing unnecessary backtracking while improving reasoning quality. By strategically delegating reflective steps to a more capable model, our method significantly boosts the reasoning accuracy of reasoning models while shortening their output. With the assistance of the 32B reasoning model, the 1.5B model's accuracy on MATH500 increases from 83.2% to 89.4%, marking a substantial improvement of 6.2%. Simultaneously, the average output length is reduced from 5439 tokens to 4583 tokens, representing a 15.7% decrease. Moreover, when applied to a non-reasoning model (Qwen-2.5-7B-Instruct), our framework boosts its accuracy from 74.0% to 81.8% on the same benchmark, achieving a relative improvement of 7.8%.
title Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2504.12329