SOURCE-LINKED INTELLIGENCE

What It Costs to Compose, Rebuild, and Correct Precomputed Memory

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

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 phr

Read original source ↗ Open in workspace

recordType

paper

region

Global