Efficient Reasoning Models: A Survey

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Sicheng, Fang, Gongfan, Ma, Xinyin, Wang, Xinchao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908564479541248
author Feng, Sicheng
Fang, Gongfan
Ma, Xinyin
Wang, Xinchao
author_facet Feng, Sicheng
Fang, Gongfan
Ma, Xinyin
Wang, Xinchao
contents Reasoning models have demonstrated remarkable progress in solving complex and logic-intensive tasks by generating extended Chain-of-Thoughts (CoTs) prior to arriving at a final answer. Yet, the emergence of this "slow-thinking" paradigm, with numerous tokens generated in sequence, inevitably introduces substantial computational overhead. To this end, it highlights an urgent need for effective acceleration. This survey aims to provide a comprehensive overview of recent advances in efficient reasoning. It categorizes existing works into three key directions: (1) shorter - compressing lengthy CoTs into concise yet effective reasoning chains; (2) smaller - developing compact language models with strong reasoning capabilities through techniques such as knowledge distillation, other model compression techniques, and reinforcement learning; and (3) faster - designing efficient decoding strategies to accelerate inference of reasoning models. A curated collection of papers discussed in this survey is available in our GitHub repository: https://github.com/fscdc/Awesome-Efficient-Reasoning-Models.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10903
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Reasoning Models: A Survey
Feng, Sicheng
Fang, Gongfan
Ma, Xinyin
Wang, Xinchao
Computation and Language
Artificial Intelligence
Reasoning models have demonstrated remarkable progress in solving complex and logic-intensive tasks by generating extended Chain-of-Thoughts (CoTs) prior to arriving at a final answer. Yet, the emergence of this "slow-thinking" paradigm, with numerous tokens generated in sequence, inevitably introduces substantial computational overhead. To this end, it highlights an urgent need for effective acceleration. This survey aims to provide a comprehensive overview of recent advances in efficient reasoning. It categorizes existing works into three key directions: (1) shorter - compressing lengthy CoTs into concise yet effective reasoning chains; (2) smaller - developing compact language models with strong reasoning capabilities through techniques such as knowledge distillation, other model compression techniques, and reinforcement learning; and (3) faster - designing efficient decoding strategies to accelerate inference of reasoning models. A curated collection of papers discussed in this survey is available in our GitHub repository: https://github.com/fscdc/Awesome-Efficient-Reasoning-Models.
title Efficient Reasoning Models: A Survey
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2504.10903