71
AI 评分(两次独立评分的平均)NVIDIA 论文提出将 LLM 推理轨迹缓存为 CPU 可执行代码
原标题:New NVIDIA paper finds that once an LLM has reasoned through a problem, the solution can run as CPU code for rephrased and re-numbered ve...
NVIDIA 新论文提出,LLM 推理过一个问题后,可把推理轨迹转成带可调参数的小型 Python 函数,在 CPU 上运行以回答改写或换数字的同类问题,成本降低 16 到 291 倍。
中文译文尚未完成,先为你展示原文。
New NVIDIA paper finds that once an LLM has reasoned through a problem, the solution can run as CPU code for rephrased and re-numbered versions of it.
that answers similar questions 16x to 291x cheaper.
LLMs re-solve every problem from scratch, even when only wording or numbers change. Agents sending the same instructions with new data pay for that repeated reasoning each time.
Their method has Claude Opus 4.5 turn a reasoning trace into small Python functions, with changeable inputs as parameters. At run time they execute on a CPU, calling a fine-tuned 1B model only for small text jobs like extracting values.
The cache matched or beat the source model's accuracy on 7 of 8 math and science benchmarks, scoring 93.3% versus 83.3% on AIME '25. It handled at least 90% of rephrased or re-numbered variants.
If your agent runs the same prompt on new inputs all day, cache the reasoning as code and use the LLM only on misses.
