让智能体长期记忆不退化，通过动态调整记忆结构保持高效检索。
All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution
- 用可编辑的拓扑结构存储记忆，避免传统压缩导致的信息丢失。
- 在线检索限定在有限区域，离线时由大模型提出优化建议并执行。
- 适合需要长期记忆的对话系统、个人助理等场景。
长期交互式智能体需在数月甚至数年内持续记录并准确召回记忆，但现有系统随历史增长易出现冗余、过时或噪声信息。本文提出 All-Mem，一种支持在线/离线操作的终身记忆框架，通过显式、非破坏性整合构建拓扑结构化的记忆库，避免基于摘要压缩带来的不可逆信息损失。在线运行时，检索锚定于有限可见表面，保证粗粒度搜索开销可控；离线周期中，由大模型诊断器提出带置信度评分的拓扑修改建议，并通过分裂、合并、更新三类操作实现，同时保留不可变证据以保障可追溯性。查询时，类型化链接支持在预算内从活跃锚点向归档证据进行跳数受限的扩展。在 LoCoMo 与 LongMemEval-s 数据集上的实验表明，其检索与问答性能优于代表性基线方法。代码已开源。
原文摘要 · Abstract (English)
Lifelong interactive agents are expected to assist users over months or years, which requires continually writing long term memories while retrieving the right evidence for each new query under fixed context and latency budgets. Existing memory systems often degrade as histories grow, yielding redundant, outdated, or noisy retrieved contexts. We present \textbf{All-Mem}, an online/offline lifelong memory framework that maintains a topology structured memory bank via explicit, non destructive consolidation, avoiding the irreversible information loss typical of summarization based compression. In online operation, it anchors retrieval on a bounded visible surface to keep coarse search cost bounded. Periodically offline, an LLM diagnoser proposes confidence scored topology edits executed with gating using three operators: Split, Merge, and Update, while preserving immutable evidence for traceability. At query time, typed links enable hop bounded, budgeted expansion from active anchors to archived evidence when needed. Experiments on \textbf{LoCoMo} and \textbf{LongMemEval-s} show improved retrieval and QA over representative baselines. The code is available at https://github.com/LvCan926/All-Mem.
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。