大规模推理模型的高效推理研究综述：语言、多模态及更广阔领域

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond

March 27, 2025

作者: Xiaoye Qu, Yafu Li, Zhaochen Su, Weigao Sun, Jianhao Yan, Dongrui Liu, Ganqu Cui, Daizong Liu, Shuxian Liang, Junxian He, Peng Li, Wei Wei, Jing Shao, Chaochao Lu, Yue Zhang, Xian-Sheng Hua, Bowen Zhou, Yu Cheng

cs.AI

摘要

近期的大型推理模型（LRMs），如DeepSeek-R1和OpenAI o1，通过扩展推理过程中的思维链（CoT）长度，展现了显著的性能提升。然而，一个日益凸显的问题是这些模型倾向于生成过长的推理轨迹，其中常充斥着冗余内容（例如重复的定义）、对简单问题的过度分析，以及对复杂任务多推理路径的浅层探索。这种低效性在训练、推理及实际部署（如基于代理的系统中）带来了重大挑战，尤其是在令牌经济性至关重要的场景下。本综述全面回顾了近期旨在提升LRMs推理效率的研究进展，特别聚焦于这一新范式中出现的独特挑战。我们识别了低效性的常见模式，考察了从预训练到推理整个LRM生命周期中提出的改进方法，并探讨了未来研究的潜在方向。为支持持续发展，我们还维护了一个实时更新的GitHub仓库，追踪该领域的最新进展。我们希望本综述能为进一步探索奠定基础，并激发这一快速演进领域的创新。

English

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.