Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability· 代理的记忆能否在模型升级中幸存？
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 \p
研究模型升级对代理记忆的影响，探索不同记忆存储方式的迁移性。
- 核心方法
- 比较四种记忆存储方式（LC-RAW、RAG、NOTES、KG-fixed）在模型升级后的记忆迁移效果，使用合成历史数据和精确评分进行评估。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 模型升级可能导致代理记忆丢失或解释变化，影响记忆的可移植性。
- 关键实验
- 实验使用48个合成历史数据，随机答案代码，精确评分，以及两个参数量小于10亿的开放权重模型。
- 主要贡献
- 揭示固定模式结构在模型升级中具有较高的记忆迁移可靠性，为模型升级时保护代理记忆提供指导。
- 意义与局限
- 本研究有助于理解模型升级对代理记忆的影响，为设计更稳定、可靠的记忆系统提供参考。局限在于使用的模型参数较少，可能不完全适用于大型模型。