模型升级是例行公事，而 3B 内存迁移则不然。代理可以保留相同的内存存储，但仍然会忘记:新模型可能会以不同的方式解释旧笔记,混合嵌入版本可能会破坏检索,并且在没有原始证据的情况下修复可能会失败。我们比较记忆，因为相同的历史记录被逐字保留以用于长上下文阅读(LC-RAW),，分为用于检索增强生成的块(RAG),，由模型压缩为自然语言注释(NOTES),或标准化为固定模式知识图(KG-fixed)。该研究使用 48 个综合历史记录，其中包含随机答案代码, 精确评分, 和两个具有不到 100 亿个参数的开放权重模型。我们的测量表明，固定模式结构可靠地传输,，KG 固定精度在写入器交换后仅变化$+0.0004 \pm 0.0020$。相反，, 压缩的NOTES 表现出高模型耦合,，根据具体的迁移方向，精度会不对称地偏移$+9.91$ 或$-13.28$ 个百分点。在 RAG 系统中，使用 50/50 混合索引的, 部分嵌入迁移仅捕获了 4.96 点精度改进, 丧失了通过完全重新嵌入实现的 11.90 点增益的大部分。诊断分解将NOTES准确性缺陷的80% ($0.467 \pm 0.014$)归因于初始构建,期间丢失的信息，而检索失败则导致RAG缺陷的81% ($0.364 \pm 0.012$)。最后, 仅存储修复NOTES 未能在所有 48 个测试用例中达到 90% 的性能恢复目标,，而保留原始源历史记录可以在一个测试方向的 48 个用例中的 34 个用例中成功恢复。这些发现强调了特定方向迁移测试,、严格嵌入空间隔离, 以及保留源历史记录以进行内存修复的必要性。
Model upgrades are routine; memory migrations are not. An agent can keep the same memory store and still forget: a new model may interpret old notes differently, mixed embedding versions may break retrieval, and repair may fail without the original evidence. We compare memory as the same history is preserved verbatim for long-context reading (LC-RAW), divided into chunks for retrieval-augmented generation (RAG), compressed by a model into natural-language notes (NOTES), or normalized into a fixed-schema knowledge graph (KG-fixed). The study uses 48 synthetic histories with randomized answer codes, exact scoring, and two open-weight models with sub 10 billion parameters. Our measurements show that fixed-schema structures transfer reliably, with KG-fixed accuracy changing by only $+0.0004 \pm 0.0020$ following a writer swap. Conversely, compressed NOTES exhibit high model coupling, with accuracy shifting asymmetrically by $+9.91$ or $-13.28$ percentage points depending on the specific migration direction. In RAG systems, partial embedding migrations using a 50/50 mixed index capture only a 4.96-point accuracy improvement, forfeiting the majority of the 11.90-point gain achieved through full re-embedding. Diagnostic decomposition attributes 80% ($0.467 \pm 0.014$) of the NOTES accuracy deficit to information lost during initial construction, whereas retrieval failures drive 81% ($0.364 \pm 0.012$) of the RAG deficit. Finally, store-only repair of NOTES fails to reach a 90% performance recovery target in all 48 test cases, whereas retaining the raw source history enables successful recovery in 34 of 48 cases for one tested direction. These findings highlight the necessity of direction-specific migration testing, strict embedding space isolation, and the retention of source histories for memory repair.
科目: 人工智能 (cs.AI); 计算和语言 (cs.CL); 信息检索 (cs.IR)
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR)