让AI把临时提示变成永久记忆
大模型很健忘：你给它一段背景资料，它回答得更好，但对话一结束，这些好处就全丢了。这篇论文把生物大脑的「记忆巩固」机制搬进AI——模型在回答问题时，会主动生成一些「未来可能被问到的问题」，把当前上下文里的知识蒸馏成一组可合并的微小参数补丁，直接写进模型本身。在14B参数的模型上连续改50次事实后，它保留了89%的上下文带来的提升，同时原有能力几乎无损。这不是你明天能用的功能，但它指向一个方向：AI不再靠每次对话临时喂资料，而是像人一样，把有用的东西真正记住。
📄 原文摘要(英文)
Context can improve large language model performance, but these gains may be lost after context removal. Inspired by biological systems consolidation, we formulate Memory Consolidation (MC) as internalizing these gains while preserving non-target capabilities, connecting context-specified editing, skill learning, and behavioral steering under a common objective. We introduce a five-task-family testbed measuring consolidation and retention under single, batch, and sequential updates. We propose Cortex, which generates prospective queries to anticipate uses of context and distills context-conditioned outputs into mergeable low-rank or structural feed-forward network updates. Across 4B--120B dense and mixture-of-experts backbones, including both text-only and multimodal models, Cortex lies on the empirical consolidation--retention Pareto frontier in most evaluated settings. After 50 sequential factual edits on a 14B model, Cortex-Structural recovers 88.9% of the context-induced gain while retaining 99.8% of original non-target performance.