Large Language Model (LLM) agents exhibit remarkable conversational and reasoning capabilities but remain constrained by limited context windows and the lack of persistent memory. Recent efforts address these limitations via external memory architectures, often employing graph-based representations, yet most adopt flat, entangled structures that intertwine semantics with topology, leading to redundant representations, unstructured retrieval, and degraded efficiency and accuracy. To resolve these issues, we propose LiCoMemory, an end-to-end agentic memory framework for real-time updating and retrieval, which introduces CogniGraph, a lightweight hierarchical graph that utilizes entities and relations as semantic indexing layers, and employs temporal and hierarchy-aware search with integrated reranking for adaptive and coherent knowledge retrieval. Experiments on long-term dialogue benchmarks, LoCoMo and LongMemEval, show that LiCoMemory not only outperforms established baselines in temporal reasoning, multi-session consistency, and retrieval efficiency, but also notably reduces update latency. Our official code and data are available at https://github.com/EverM0re/LiCoMemory.

翻译：大型语言模型（LLM）智能体展现出卓越的对话与推理能力，但仍受限于有限的上下文窗口和缺乏持久记忆。近期研究通过外部记忆架构来解决这些限制，通常采用基于图的表示方法，然而多数方案采用扁平、纠缠的结构，将语义与拓扑交织在一起，导致冗余表示、非结构化检索以及效率和准确性的下降。为解决这些问题，我们提出了LiCoMemory，一个用于实时更新与检索的端到端代理记忆框架。该框架引入了CogniGraph——一种轻量级层次图，利用实体和关系作为语义索引层，并采用结合时间与层次感知的搜索策略，配合集成重排序机制，以实现自适应且连贯的知识检索。在长期对话基准测试（LoCoMo与LongMemEval）上的实验表明，LiCoMemory不仅在时序推理、多会话一致性及检索效率方面优于现有基线，还显著降低了更新延迟。我们的官方代码与数据可在 https://github.com/EverM0re/LiCoMemory 获取。