A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
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_ | 1866916719148138496 |
|---|---|
| author | Zhang, Qiyuan Lyu, Fuyuan Sun, Zexu Wang, Lei Zhang, Weixu Hua, Wenyue Wu, Haolun Guo, Zhihan Wang, Yufei Muennighoff, Niklas King, Irwin Liu, Xue Ma, Chen |
| author_facet | Zhang, Qiyuan Lyu, Fuyuan Sun, Zexu Wang, Lei Zhang, Weixu Hua, Wenyue Wu, Haolun Guo, Zhihan Wang, Yufei Muennighoff, Niklas King, Irwin Liu, Xue Ma, Chen |
| contents | As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing'' has emerged as a prominent research focus. Recent studies demonstrate that TTS can further elicit the problem-solving capabilities of large language models (LLMs), enabling significant breakthroughs not only in specialized reasoning tasks, such as mathematics and coding, but also in general tasks like open-ended Q&A. However, despite the explosion of recent efforts in this area, there remains an urgent need for a comprehensive survey offering a systemic understanding. To fill this gap, we propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale. Building upon this taxonomy, we conduct an extensive review of methods, application scenarios, and assessment aspects, and present an organized decomposition that highlights the unique functional roles of individual techniques within the broader TTS landscape. From this analysis, we distill the major developmental trajectories of TTS to date and offer hands-on guidelines for practical deployment. Furthermore, we identify several open challenges and offer insights into promising future directions, including further scaling, clarifying the functional essence of techniques, generalizing to more tasks, and more attributions. Our repository is available on https://github.com/testtimescaling/testtimescaling.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_24235 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well? Zhang, Qiyuan Lyu, Fuyuan Sun, Zexu Wang, Lei Zhang, Weixu Hua, Wenyue Wu, Haolun Guo, Zhihan Wang, Yufei Muennighoff, Niklas King, Irwin Liu, Xue Ma, Chen Computation and Language Artificial Intelligence As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing'' has emerged as a prominent research focus. Recent studies demonstrate that TTS can further elicit the problem-solving capabilities of large language models (LLMs), enabling significant breakthroughs not only in specialized reasoning tasks, such as mathematics and coding, but also in general tasks like open-ended Q&A. However, despite the explosion of recent efforts in this area, there remains an urgent need for a comprehensive survey offering a systemic understanding. To fill this gap, we propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale. Building upon this taxonomy, we conduct an extensive review of methods, application scenarios, and assessment aspects, and present an organized decomposition that highlights the unique functional roles of individual techniques within the broader TTS landscape. From this analysis, we distill the major developmental trajectories of TTS to date and offer hands-on guidelines for practical deployment. Furthermore, we identify several open challenges and offer insights into promising future directions, including further scaling, clarifying the functional essence of techniques, generalizing to more tasks, and more attributions. Our repository is available on https://github.com/testtimescaling/testtimescaling.github.io/ |
| title | A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well? |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.24235 |