通过推理技能思考：更少的标记，更高的准确性
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
AI总结：
本文提出通过存储和检索推理技能来减少推理标记并提升性能，适用于编码和数学推理任务。
摘要：
推理大型语言模型在解决新问题时通常会消耗大量标记用于长的中间推理轨迹（例如思维链）。我们提出总结并存储从大量思考和试错探索中提炼出的可重用推理技能，并在推理时检索这些技能以指导未来推理。与传统的从头推理范式不同，我们的方法首先为每个查询召回相关技能，帮助模型避免冗余绕路并专注于有效解决方案路径。我们在编码和数学推理任务上评估了我们的方法，发现它显著减少了推理标记同时提高了整体性能。由此产生的较低的每请求成本表明了在现实世界部署中的强大实用性和经济潜力。
英文摘要：
Reasoning LLMs often spend substantial tokens on long intermediate reasoning traces (e.g., chain-of-thought) when solving new problems. We propose to summarize and store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration, and to retrieve these skills at inference time to guide future reasoning. Unlike the prevailing \emph{reasoning from scratch} paradigm, our approach first recalls relevant skills for each query, helping the model avoid redundant detours and focus on effective solution paths. We evaluate our method on coding and mathematical reasoning tasks, and find that it significantly reduces reasoning tokens while improving overall performance. The resulting lower per-request cost indicates strong practical and economic potential for real-world deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
