跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.09891 · v1

CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse

CPU-ARC:面向CPU推理复用的智能体推理缓存

首次提交 2026-11-07 02:58
版本更新 2026-11-07 02:58
雷达观测 2026-11-09 13:22
arXiv ↗PDF ↗

摘要

Large language models reinvent the wheel all the time. They conflate task-solving with the execution of the solutions, which forces them to solve every problem from scratch. We show that once a task has been reasoned through, the application of its solution to a new problem instance can be done very efficiently and with little involvement from language models. We introduce agentic reasoning caching, a method for constructing robust CPU-executable agentic reasoning caches (ARCs) from LLM reasoning traces. ARCs show on-par performance with frontier LLMs across a range of difficult mathematical and scientific tasks, are fully explainable, continually trainable, robust to input perturbations, and 16-291x cheaper to invoke than the source model.

作者备注:Tech report. 28 pages, 9 figures, 11 tables

AI 论文解读

基于摘要 · 非全文审阅

作者提出智能体推理缓存(ARCs),把大模型的推理轨迹转化为可在CPU上执行的缓存,使已推理过的问题解法能高效复用于新实例,从而减少对大模型的重复调用。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-07 02:58 · 最新观测版本

CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse

Large language models reinvent the wheel all the time. They conflate task-solving with the execution of the solutions, which forces them to solve every problem from scratch. We show that once a task has been reasoned through, the application of its solution to a new problem instance can be done very efficiently and with little involvement from language models. We introduce agentic reasoning caching, a method for constructing robust CPU-executable agentic reasoning caches (ARCs) from LLM reasoning traces. ARCs show on-par performance with frontier LLMs across a range of difficult mathematical and scientific tasks, are fully explainable, continually trainable, robust to input perturbations, and 16-291x cheaper to invoke than the source model.

查看此版本解读 →查看此版本原文 ↗