用可复用的推理技能减少大模型思考耗时，提升准确率
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
- 把反复试错中提炼的推理技能存下来，推理时直接调用
- 在编程和数学任务上减少大量中间思考步骤，准确率反而提高
- 适合追求高效推理、降低部署成本的研究者与开发者
推理型大模型在解决新问题时常需耗费大量 token 生成冗长的中间推理过程（如思维链）。本文提出将经过广泛推敲与试错积累的可复用推理技能进行提炼并存储，在推理时检索使用，以引导后续推理。与传统的“从零开始推理”范式不同，本方法先针对查询召回相关技能，帮助模型避开重复路径，聚焦有效解题路线。我们在编码和数学推理任务上评估该方法，结果表明其显著减少了推理 token 数量，同时提升了整体性能。更低的单次请求成本显示出其在真实场景部署中的强大实用价值与经济潜力。
原文摘要 · Abstract (English)
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.
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。