论文用Qwen3-8B做实验，发现KV缓存里的事件行能独立保存计算视图，主动构造回答无关事件能让恢复率从6%跳到51%，对搞Agent记忆的人很有参考价值。
这篇论文研究了长时程智能体复用KV缓存作为记忆时的语义具体化现象。实验发现，在Qwen3-8B上，通过构造不含答案的事件，可将关联值恢复率从6%提升到51%。作者指出，被动从对话中提取自然提及没有检测到优势，而主动构造特定表述能显著影响记忆写入。结果表明，稀疏事件KV服务存在记忆契约：写入什么、落在哪里、源事件消失后保留什么，都有明确规律。
Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV
Long-horizon agents increasingly reuse their KV cache as memory: a serving system keeps a subset of cached entries and drops the rest. Eviction and episodic-memory schemes therefore rest on a premise rarely tested directly, that a retained event is still informative once the observations that produced it are gone. We test it by omitting one earlier observation from what is served, across otherwise identical agent histories. Among items sensitive to that observation, the answer overwhelmingly follows the omitted value, though no served span says which value is correct. We call this semantic materialization: a downstream event's cached rows act as an independently servable view of computation whose inputs are gone. It can also be written on purpose. A deliberately phrased, answer-free event raises donor-aligned recovery from 6% to 51% on Qwen3-8B without ever naming the value, whereas passively harvesting natural mentions from long-term dialog yields no detected advantage. What such a row carries is specific and bounded. Compact state survives, larger payloads decay toward chance, and whether a construction writes at all turns on phrasing rather than on meaning alone, so two phrasings the model comprehends equally well can diverge sharply. The result is a memory contract for sparse event-KV serving: what to write, where it lands, and what survives once the source is gone. For anyone who evicts the corollary is that dropping a source event and observing no accuracy loss does not show the source was unnecessary.