Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.21614 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912795961851904 |
|---|---|
| author | Qu, Xiaoye Li, Yafu Su, Zhao-Chen Sun, Weigao Yan, Jianhao Liu, Dongrui Cui, Ganqu Liu, Daizong Liang, Shuxian He, Junxian Li, Peng Wei, Wei Shao, Jing Lu, Chaochao Zhang, Yue Hua, Xian-Sheng Zhou, Bowen Cheng, Yu |
| author_facet | Qu, Xiaoye Li, Yafu Su, Zhao-Chen Sun, Weigao Yan, Jianhao Liu, Dongrui Cui, Ganqu Liu, Daizong Liang, Shuxian He, Junxian Li, Peng Wei, Wei Shao, Jing Lu, Chaochao Zhang, Yue Hua, Xian-Sheng Zhou, Bowen Cheng, Yu |
| contents | Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference. However, a growing concern lies in their tendency to produce excessively long reasoning traces, which are often filled with redundant content (e.g., repeated definitions), over-analysis of simple problems, and superficial exploration of multiple reasoning paths for harder tasks. This inefficiency introduces significant challenges for training, inference, and real-world deployment (e.g., in agent-based systems), where token economy is critical. In this survey, we provide a comprehensive overview of recent efforts aimed at improving reasoning efficiency in LRMs, with a particular focus on the unique challenges that arise in this new paradigm. We identify common patterns of inefficiency, examine methods proposed across the LRM lifecycle, i.e., from pretraining to inference, and discuss promising future directions for research. To support ongoing development, we also maintain a real-time GitHub repository tracking recent progress in the field. We hope this survey serves as a foundation for further exploration and inspires innovation in this rapidly evolving area. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21614 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond Qu, Xiaoye Li, Yafu Su, Zhao-Chen Sun, Weigao Yan, Jianhao Liu, Dongrui Cui, Ganqu Liu, Daizong Liang, Shuxian He, Junxian Li, Peng Wei, Wei Shao, Jing Lu, Chaochao Zhang, Yue Hua, Xian-Sheng Zhou, Bowen Cheng, Yu Computation and Language Recent Large Reasoning Models (LRMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated strong performance gains by scaling up the length of Chain-of-Thought (CoT) reasoning during inference. However, a growing concern lies in their tendency to produce excessively long reasoning traces, which are often filled with redundant content (e.g., repeated definitions), over-analysis of simple problems, and superficial exploration of multiple reasoning paths for harder tasks. This inefficiency introduces significant challenges for training, inference, and real-world deployment (e.g., in agent-based systems), where token economy is critical. In this survey, we provide a comprehensive overview of recent efforts aimed at improving reasoning efficiency in LRMs, with a particular focus on the unique challenges that arise in this new paradigm. We identify common patterns of inefficiency, examine methods proposed across the LRM lifecycle, i.e., from pretraining to inference, and discuss promising future directions for research. To support ongoing development, we also maintain a real-time GitHub repository tracking recent progress in the field. We hope this survey serves as a foundation for further exploration and inspires innovation in this rapidly evolving area. |
| title | A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.21614 |