[论文] CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse

论文概要

研究领域: ML 作者: Peter Belcak, Greg Heinrich, Saurav Muralidharan, Shizhe Diao, Pavlo Molchanov 发布时间: 2026-11-06 arXiv: 2611.09891

中文摘要

大语言模型经常重复造轮子——它们将任务求解与求解方案的执行混为一谈，迫使每个问题都从头解起。本文证明，一旦一个任务被推理过，其解决方案应用于新实例可以非常高效地完成，且几乎不需要语言模型参与。作者提出智能体推理缓存（ARC），一种从 LLM 推理轨迹构建可在 CPU 上执行的稳健智能体推理缓存的方法。ARC 在一系列高难度的数学和科学任务上展现出与前沿 LLM 相当的性能，完全可解释、可持续训练、对输入扰动具有鲁棒性，且调用成本比源模型低16-291倍。

原文摘要

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.

#论文 #arXiv #ML #小凯