Stage-Replay Divergence Follows the KV Cache: Fixed-Prefix Precision Controls and Bidirectional Cache Transplantation

AI 中文解读

人类把AI“喂”了同样的输入，按理说应该得到同样的回答。但最新研究发现，在特定情况下，AI的“记忆”方式不同，就会让回答产生细微偏差。更关键的是，AI中间缓存的那层“思路底稿”，几乎决定了它最终往哪个方向走。这项研究就像给AI做了一次“思维对比实验”。他们用完全相同的问题，分别让AI通过两种方式回答：一种保留着计算过程中的临时记忆，另一种从零开始重新算。结果显示，在常用精度下，两种方式有166个结果出现差异，准确率差1分；但把精度提升到更高标准后，差异完全消失。这对普通人的意义在于，AI的“脾气”其实比我们想的更敏感。你用同样的方式问同一个AI，结果可能并不完全一致，尤其在需要精确数学或逻辑推理的场合。好消息是，只要把计算精度调高，或者保留好AI的“工作底稿”，就能让AI更加稳定可靠。这项研究也为以后开发更“靠谱”的AI助手提供了重要线索——想让它说什么，先把它的“记忆状态”管好。

Stage-replay diagnostics reconstruct intermediate token prefixes and treat fresh-prefill continuation as continuation from the decoder state that originally reached the prefix. We audit that assumption at a whole reasoning-stage boundary in a Qwen2.5-derived system. A matched 200-item experiment compares retained live cache with one-shot prefill of identical integer tokens and places an exact replica on both sides. In BF16, replicas remain exact while the constructions differ on 166 suffixes and 20 correctness labels; the accuracy difference is only one point (paired 95% CI [-3.5, +5.5]). A fixed-prefix 2x2 holds all 200 token states constant while crossing construction and precision. The BF16 disagreements recur, whereas FP32 produces no decoded disagreement (95% Wilson upper bound 1.88%). A prospective bridge makes token-by-token incremental and retained live caches bit-exact on 12/12 rows; an all-200 saved-ledger audit reproduces every retained trajectory and comparison fingerprint. Bidirectional transplantation of all 48 key/value layers makes every tested divergent continuation follow its cache donor, both on a selected set at the primary checkpoint (24/24) and an outcome-blind replication at a later checkpoint (43/43). Exact-token replay can therefore be repeatable without preserving live-state fidelity. On the tested states, boundary K/V cache is a causally sufficient carrier of the divergent trajectory, while numerical precision moderates its behavioral expression.