Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless lookup table: information persists indefinitely, retrieval is read-only, and temporal continuity is absent. We define the \textit{Continuum Memory Architecture} (CMA), a class of systems that maintain and update internal state across interactions through persistent storage, selective retention, associative routing, temporal chaining, and consolidation into higher-order abstractions. Rather than disclosing implementation specifics, we specify the architectural requirements CMA imposes and show consistent behavioral advantages on tasks that expose RAG's structural inability to accumulate, mutate, or disambiguate memory. The empirical probes (knowledge updates, temporal association, associative recall, contextual disambiguation) demonstrate that CMA is a necessary architectural primitive for long-horizon agents while highlighting open challenges around latency, drift, and interpretability.

翻译：检索增强生成（RAG）已成为为大型语言模型（LLM）智能体提供上下文知识的默认策略。然而，RAG将记忆视为一种无状态的查找表：信息无限期持续存在，检索是只读的，且缺乏时间连续性。我们定义了\textit{连续记忆架构}（CMA），这是一类通过持久化存储、选择性保留、关联路由、时间链式连接以及整合为更高阶抽象，在交互过程中维护和更新内部状态的系统。我们并未披露具体实现细节，而是明确了CMA所要求的架构规范，并在那些暴露RAG在记忆累积、变更或消歧方面存在结构性缺陷的任务上，展示了其一致的行为优势。实证探究（知识更新、时间关联、关联回忆、上下文消歧）表明，CMA是实现长周期智能体所必需的架构原语，同时也凸显了在延迟、漂移和可解释性方面存在的开放挑战。