The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requires maintaining rigorous logical integrity over extended horizons. However, prevalent memory preprocessing paradigms suffer from destructive de-contextualization. By compressing complex sequential dependencies into pre-defined structures (e.g., embeddings or graphs), these methods sever the contextual integrity essential for deep reasoning. To address this, we propose E-mem, a framework shifting from Memory Preprocessing to Episodic Context Reconstruction. Inspired by biological engrams, E-mem employs a heterogeneous hierarchical architecture where multiple assistant agents maintain uncompressed memory contexts, while a central master agent orchestrates global planning. Unlike passive retrieval, our mechanism empowers assistants to locally reason within activated segments, extracting context-aware evidence before aggregation. Evaluations on the LoCoMo benchmark demonstrate that E-mem achieves over 54\% F1, surpassing the state-of-the-art GAM by 7.75\%, while reducing token cost by over 70\%.

翻译：大语言模型代理向系统2推理的演进——以深思熟虑、高精度的问题求解为特征——需要跨越扩展时间视野保持严格的逻辑完整性。然而，当前主流的记忆预处理范式存在破坏性的去语境化缺陷。通过将复杂的序列依赖关系压缩为预定义结构（如嵌入或图），这些方法割裂了深层推理所必需的上下文完整性。为解决此问题，我们提出E-mem框架，实现从记忆预处理到情节上下文重建的范式转换。受生物印迹启发，E-mem采用异构分层架构：多个辅助代理维护未压缩的记忆上下文，中央主代理负责全局规划协调。与被动检索不同，该机制使辅助代理能在激活片段内进行局部推理，在聚合前提取具有上下文感知的证据。在LoCoMo基准上的评估显示，E-mem取得超过54%的F1分数，以7.75%的绝对优势超越当前最优的GAM方法，同时降低70%以上的令牌成本。