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

Peter Belcak, Greg Heinrich, Saurav Muralidharan, Shizhe Diao, Pavlo Molchanov

CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse: 11 upvotes on Hugging Face Daily Papers, #18 of 34 papers on 2026-11-09. Day-by-day upvote history.

Upvotes over time

It had 6 upvotes by its first day, 10 upvotes by the next day, 11 upvotes by day 3, 11 upvotes by day 7, and has 11 now. It ranked #54 of 133 papers in its week and #160 of 340 in its month.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.