Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |