Saved in:
Bibliographic Details
Main Authors: Yang, Zhuoyi, Guo, Xu, Zhang, Tong, Xu, Huijuan, Li, Boyang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.14772
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917090122792960
author Yang, Zhuoyi
Guo, Xu
Zhang, Tong
Xu, Huijuan
Li, Boyang
author_facet Yang, Zhuoyi
Guo, Xu
Zhang, Tong
Xu, Huijuan
Li, Boyang
contents With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time scaling methods, we place special emphasis on how a problem is decomposed into subproblems and on the topological organization of these subproblems whether sequential, parallel, or tree-structured. This perspective allows us to unify diverse approaches such as Chain-of-Thought, Branch-Solve-Merge, and Tree-of-Thought under a common lens. We further synthesize existing analyses of these techniques, highlighting their respective strengths and weaknesses, and conclude by outlining promising directions for future research
format Preprint
id arxiv_https___arxiv_org_abs_2511_14772
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective
Yang, Zhuoyi
Guo, Xu
Zhang, Tong
Xu, Huijuan
Li, Boyang
Computation and Language
Artificial Intelligence
With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time scaling methods, we place special emphasis on how a problem is decomposed into subproblems and on the topological organization of these subproblems whether sequential, parallel, or tree-structured. This perspective allows us to unify diverse approaches such as Chain-of-Thought, Branch-Solve-Merge, and Tree-of-Thought under a common lens. We further synthesize existing analyses of these techniques, highlighting their respective strengths and weaknesses, and conclude by outlining promising directions for future research
title Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.14772