小推理模型高效实现复杂任务，适合资源受限场景。
A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions
- 从大模型蒸馏出小模型，提升推理效率。
- 涵盖170篇论文，系统梳理训练与推理技术。
- 适合想高效实现智能推理的研究者参考。
近期，大型推理模型（如 DeepSeek-R1）通过慢思考过程实现了显著的推理能力提升。尽管如此，大型模型巨大的计算需求仍带来挑战。相比之下，小型推理模型（SRMs）通常由大模型蒸馏而来，具有更高的效率，并可能展现出与大型模型不同的能力特征和认知路径。本文综述了约170篇近期发表的关于小推理模型（SRMs）的论文，涵盖其在各类复杂推理任务中的应用。我们系统回顾了当前SRMs的发展现状，分析了多种相关的训练与推理技术，并对特定领域的应用进行了全面总结，同时探讨了未来可能的研究方向。本综述为研究人员利用或开发高效率的高级推理功能提供重要参考。
原文摘要 · Abstract (English)
Recently, the reasoning capabilities of large reasoning models (LRMs), such as DeepSeek-R1, have seen significant advancements through the slow thinking process. Despite these achievements, the substantial computational demands of LRMs present considerable challenges. In contrast, small reasoning models (SRMs), often distilled from larger ones, offer greater efficiency and can exhibit distinct capabilities and cognitive trajectories compared to LRMs. This work surveys around 170 recently published papers on SRMs for tackling various complex reasoning tasks. We review the current landscape of SRMs and analyze diverse training and inference techniques related to SRMs. Furthermore, we provide a comprehensive review of SRMs for domain-specific applications and discuss possible future research directions. This survey serves as an essential reference for researchers to leverage or develop SRMs for advanced reasoning functionalities with high efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。