论文揭示了预计算内存的重建成本和更新策略，对优化大模型上下文处理有实用价值。
该论文研究了Llama-3.1-8B-Instruct模型中预计算内存的保存与修正问题。实验表明，预计算内存由单独准备的部分组装时会降低准确性，重建成本接近完整重新准备的很大比例。研究还发现，预计算内存会忽略基于措辞条件的修正信息。通过训练压缩的键值缓存热重建和特定措辞更新，可以在重建间隔期间保持内存更新。
What It Costs to Compose, Rebuild, and Correct Precomputed Memory
Language models can answer from precomputed memory, a model's saved reading of a body of material, reused across requests instead of read again at each. This paper maps where that practice preserves correctness and the conditions under which it fails. Across experiments on Llama-3.1-8B-Instruct using both saved key-value caches and trained compressions of them, precomputed memory degrades when assembled from separately prepared parts, stays current only through rebuilds costing a large fraction of full preparation in our measurements, and ignores corrections served beside it conditional on phrasing. If precomputed memories can be served alongside one another, be cost-efficiently rebuilt, and be superseded by new information arriving in real-time, they can serve as a way to avoid re-feeding context to a model over repeated queries. The implication of our results for a deployed system that deals with a variety of queries is that precomputed memories are best rebuilt on the cadence at which new information changes what the memory was originally computed from. Both warm-rebuilding trained compressions of key-value caches and serving specifically-phrased updates beside a memory, as pasted text or injected cache state, show particular promise for keeping precomputed memories current, the latter as an interim measure between rebuilds, and we measure the cost and name the remaining questions associated with each.