Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.16419 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915456354353152 |
|---|---|
| author | Sui, Yang Chuang, Yu-Neng Wang, Guanchu Zhang, Jiamu Zhang, Tianyi Yuan, Jiayi Liu, Hongyi Wen, Andrew Zhong, Shaochen Zou, Na Chen, Hanjie Hu, Xia |
| author_facet | Sui, Yang Chuang, Yu-Neng Wang, Guanchu Zhang, Jiamu Zhang, Tianyi Yuan, Jiayi Liu, Hongyi Wen, Andrew Zhong, Shaochen Zou, Na Chen, Hanjie Hu, Xia |
| contents | Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have further improved performance in System-2 reasoning domains like mathematics and programming by harnessing supervised fine-tuning (SFT) and reinforcement learning (RL) techniques to enhance the Chain-of-Thought (CoT) reasoning. However, while longer CoT reasoning sequences improve performance, they also introduce significant computational overhead due to verbose and redundant outputs, known as the "overthinking phenomenon". In this paper, we provide the first structured survey to systematically investigate and explore the current progress toward achieving efficient reasoning in LLMs. Overall, relying on the inherent mechanism of LLMs, we categorize existing works into several key directions: (1) model-based efficient reasoning, which considers optimizing full-length reasoning models into more concise reasoning models or directly training efficient reasoning models; (2) reasoning output-based efficient reasoning, which aims to dynamically reduce reasoning steps and length during inference; (3) input prompts-based efficient reasoning, which seeks to enhance reasoning efficiency based on input prompt properties such as difficulty or length control. Additionally, we introduce the use of efficient data for training reasoning models, explore the reasoning capabilities of small language models, and discuss evaluation methods and benchmarking. Project website: https://github.com/Eclipsess/Awesome-Efficient-Reasoning-LLMs |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16419 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Sui, Yang Chuang, Yu-Neng Wang, Guanchu Zhang, Jiamu Zhang, Tianyi Yuan, Jiayi Liu, Hongyi Wen, Andrew Zhong, Shaochen Zou, Na Chen, Hanjie Hu, Xia Computation and Language Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have further improved performance in System-2 reasoning domains like mathematics and programming by harnessing supervised fine-tuning (SFT) and reinforcement learning (RL) techniques to enhance the Chain-of-Thought (CoT) reasoning. However, while longer CoT reasoning sequences improve performance, they also introduce significant computational overhead due to verbose and redundant outputs, known as the "overthinking phenomenon". In this paper, we provide the first structured survey to systematically investigate and explore the current progress toward achieving efficient reasoning in LLMs. Overall, relying on the inherent mechanism of LLMs, we categorize existing works into several key directions: (1) model-based efficient reasoning, which considers optimizing full-length reasoning models into more concise reasoning models or directly training efficient reasoning models; (2) reasoning output-based efficient reasoning, which aims to dynamically reduce reasoning steps and length during inference; (3) input prompts-based efficient reasoning, which seeks to enhance reasoning efficiency based on input prompt properties such as difficulty or length control. Additionally, we introduce the use of efficient data for training reasoning models, explore the reasoning capabilities of small language models, and discuss evaluation methods and benchmarking. Project website: https://github.com/Eclipsess/Awesome-Efficient-Reasoning-LLMs |
| title | Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.16419 |