让大模型学会快慢思考，回答简单问题更简洁高效。
Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
- 提出快慢思维自适应机制，根据问题难易动态调整推理长度。
- 解决长推理链冗余问题，显著减少简单问题的计算开销。
- 适合关注推理效率与实用落地的研究者与工程师。
大型推理模型（LRMs）如 OpenAI o1 和 DeepSeek R1 在数学与编程等复杂推理任务中表现出色，依赖长链式思维（CoT）进行深度推理（慢思考），相比传统大语言模型（快思考）更具优势。然而，这些模型在面对简单问题时仍会产生冗长且不必要的推理链条，造成大量推理资源浪费，延长响应时间，阻碍其在实际产品中的应用。为此，亟需缩短冗余推理链，并学习根据输入难度在快思考与慢思考之间自适应切换。本文系统综述了近年来在提升大型推理模型推理效率方面的进展，涵盖方法论、评估基准及未来挑战。旨在帮助研究者快速掌握该领域全景，激发新的自适应推理思路，推动大型推理模型的更优应用。
原文摘要 · Abstract (English)
Large reasoning models (LRMs) like OpenAI o1 and DeepSeek R1 have demonstrated impressive performance on complex reasoning tasks like mathematics and programming with long Chain-of-Thought (CoT) reasoning sequences (slow-thinking), compared with traditional large language models (fast-thinking). However, these reasoning models also face a huge challenge that generating unnecessarily lengthy and redundant reasoning chains even for trivial questions. This phenomenon leads to a significant waste of inference resources, increases the response time for simple queries, and hinders the practical application of LRMs in real-world products. To this end, it is crucial to shorten lengthy reasoning chains and learn adaptive reasoning between fast and slow thinking based on input difficulty. In this survey, we provide a comprehensive overview of recent progress in concise and adaptive thinking for efficient reasoning of LRMs, including methodologies, benchmarks, and challenges for future exploration. We hope this survey can help researchers quickly understand the landscape of this field and inspire novel adaptive thinking ideas to facilitate better usage of LRMs.
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。