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 Existing memory systems often degrade as histories grow, yielding redundant, outdated, or noisy retrieved contexts.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 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 LOCOMO and LONGMEMEVAL show improved retrieval and QA over representative baselines.

翻译：终身交互智能体需在数月乃至数年间持续辅助用户，这就要求在固定上下文窗口与响应时延预算下，持续写入长期记忆并针对性提取正确证据。现有记忆系统随历史积累常出现性能退化，导致检索上下文存在冗余、过时或噪声问题。本文提出All-Mem框架——一种支持在线/离线模式的终身记忆系统，通过显式非破坏性整合维护拓扑结构化记忆库，避免摘要式压缩导致的不可逆信息损失。在线运行阶段，系统将检索锚定于有界可见表面以保持粗粒度搜索开销可控；离线阶段，LLM诊断器提出带置信度评分的拓扑编辑方案，经由三类算子（SPLIT分裂、MERGE合并、UPDATE更新）配合门控机制执行编辑，同时保留不可变证据确保可追溯性。查询时，系统通过带类型链接实现从活跃锚点到归档证据的有界跳数扩展与预算化扩展。在LOCOMO和LONGMEMEVAL基准上的实验表明，本方法在检索与问答任务中均优于代表性基线方法。