用多智能体重构记忆上下文，提升大模型长程推理能力
E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory
- 多智能体协作维护原始记忆上下文，避免信息丢失
- 在LoCoMo基准上F1达54%以上，比SOTA高7.75%
- 减少70%以上令牌消耗，适合复杂决策场景
大型语言模型代理向系统2式推理演进，需在长时空中保持严谨逻辑。但现有记忆预处理方法会破坏上下文连续性，将复杂的序列依赖压缩为固定结构（如嵌入或图），导致深度推理所需上下文断裂。为此，我们提出E-mem框架，从记忆预处理转向情景式上下文重建。受生物记忆痕迹启发，E-mem采用异构分层架构：多个辅助智能体维持未压缩的记忆上下文，中央主智能体负责全局规划。与被动检索不同，该机制使辅助智能体可在激活片段内本地推理，提取上下文感知证据后再聚合。在LoCoMo基准上的评估显示，E-mem实现超过54%的F1值，超越当前最优方案GAM达7.75%，同时令牌开销降低超70%。
原文摘要 · Abstract (English)
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\%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。