Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Shouren, Yang, Wang, Long, Xianxuan, Wang, Qifan, Chaudhary, Vipin, Han, Xiaotian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914092237717504
author Wang, Shouren
Yang, Wang
Long, Xianxuan
Wang, Qifan
Chaudhary, Vipin
Han, Xiaotian
author_facet Wang, Shouren
Yang, Wang
Long, Xianxuan
Wang, Qifan
Chaudhary, Vipin
Han, Xiaotian
contents Hybrid thinking enables LLMs to switch between reasoning and direct answering, offering a balance between efficiency and reasoning capability. Yet our experiments reveal that current hybrid thinking LLMs only achieve partial mode separation: reasoning behaviors often leak into the no-think mode. To understand and mitigate this, we analyze the factors influencing controllability and identify four that matter most: (1) larger data scale, (2) using think and no-think answers from different questions rather than the same question, (3) a moderate increase in no-think data number, and (4) a two-phase strategy that first trains reasoning ability and then applies hybrid think training. Building on these findings, we propose a practical recipe that, compared to standard training, can maintain accuracy in both modes while significantly reducing no-think output length (from $1085$ to $585$ on MATH500) and occurrences of reasoning-supportive tokens such as ``\texttt{wait}'' (from $5917$ to $522$ on MATH500). Our findings highlight the limitations of current hybrid thinking and offer directions for strengthening its controllability.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12680
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
Wang, Shouren
Yang, Wang
Long, Xianxuan
Wang, Qifan
Chaudhary, Vipin
Han, Xiaotian
Machine Learning
Artificial Intelligence
Computation and Language
Hybrid thinking enables LLMs to switch between reasoning and direct answering, offering a balance between efficiency and reasoning capability. Yet our experiments reveal that current hybrid thinking LLMs only achieve partial mode separation: reasoning behaviors often leak into the no-think mode. To understand and mitigate this, we analyze the factors influencing controllability and identify four that matter most: (1) larger data scale, (2) using think and no-think answers from different questions rather than the same question, (3) a moderate increase in no-think data number, and (4) a two-phase strategy that first trains reasoning ability and then applies hybrid think training. Building on these findings, we propose a practical recipe that, compared to standard training, can maintain accuracy in both modes while significantly reducing no-think output length (from $1085$ to $585$ on MATH500) and occurrences of reasoning-supportive tokens such as ``\texttt{wait}'' (from $5917$ to $522$ on MATH500). Our findings highlight the limitations of current hybrid thinking and offer directions for strengthening its controllability.
title Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.12680