| title | CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse |
|---|---|
| authors | Peter Belcak, Greg Heinrich, Saurav Muralidharan, Shizhe Diao, Pavlo Molchanov |
| date | 2026-11-06 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.09891 |
| affiliation | NVIDIA |
| upvotes | 10 (Hugging Face Daily Papers, 2026-11-11) |
| links | abs pdf hf |
| cite | |
| related | Cosmos 3: Omnimodal World Models for Physical AI LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness |
| abstract | 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. |
bibtex
@misc{belcak2026cpu,
title={CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse},
author={Peter Belcak and Greg Heinrich and Saurav Muralidharan and Shizhe Diao and Pavlo Molchanov},
year={2026},
eprint={2611.09891},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.09891}
}