把AI的思考过程压缩，能省钱吗
AI 想得越久，账单越贵。这篇试了一件很省事的事：不重训模型，只在它「想完一段、还没看到工具结果」的空档，把前面那一大段啰嗦的思考改写成一份精简的状态记录，再让它接着想。结果是被采纳的压缩版通常让后续思考变短，写代码的场景里，拿到同一个候选方案后反复验证的次数也少了。落到软件智能体上，总花费能降，但任务质量和算上改写本身的时间，取决于压缩目标和用哪个模型来压。它不是你明天就能直接用的开关——论文自己说，得针对每个模型单独调压缩策略，效率和能力要一起看。
📄 原文摘要(英文)
Reasoning substantially improves language models' ability to solve difficult problems, but long reasoning traces make these gains expensive. Efficient reasoning should express useful analysis in fewer tokens by reducing repetition and text that adds little value to solving the problem. Progress in proprietary models motivates this goal, yet their hidden scratchpads limit direct study of how it is achieved. We investigate whether open-weight models can generate less verbose reasoning by changing the form of their own earlier thoughts, without retraining. Our intervention rewrites prior reasoning into compact state records before pending tool results are revealed, then compares continuations from original and compact histories. Across the tested models, accepted compact histories usually shorten future reasoning; a coding case study also shows less repeated verification after a shared candidate solution. In software-agent deployments, compaction can reduce total spending, although task quality and rewrite-inclusive time depend on the target and compressor. These findings identify reasoning history as one way to reduce future reasoning-token use and motivate model-specific compaction policies evaluated for both efficiency and retained capability.