arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.06377cs.AI
收藏

HiMem:用于长时间跨度代理的分层长时记忆

HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents

Macau University of Science and Technology(澳门科学理工大學)

Ningning Zhang, Xingxing Yang, Zhizhong Tan, Weiping Deng, Wenyong Wang

AI总结:

HiMem通过分层长时记忆框架提升长跨度对话代理的适应性和自我进化能力,采用双通道分割和多阶段信息提取实现高效且保真的记忆管理。

摘要:

尽管长期记忆系统在近年来取得了显著进展,但在连续交互设置下仍表现出明显的适应性、可扩展性和自我进化方面的局限性。受认知理论启发,我们提出了HiMem,一种用于长跨度对话的分层长期记忆框架,旨在在持续交互中支持记忆构建、检索和动态更新。HiMem通过主题感知事件-惊讶双通道分割策略构建认知一致的事件记忆,并通过多阶段信息提取管道构建注释记忆,以捕获稳定的知识。这两种记忆类型通过语义链接形成层次结构,将具体的交互事件与抽象知识连接起来,从而实现高效的检索而不牺牲信息的保真度。HiMem支持混合和最佳努力检索策略,以在准确性和效率之间取得平衡,并结合冲突感知的记忆重固结,根据检索反馈修订和补充存储的知识。这种设计使HiMem能够在长期使用中实现持续的记忆自我进化。在长跨度对话基准上的实验结果表明,HiMem在准确度、一致性和长期推理方面始终优于代表性基线,同时保持良好的效率。总体而言,HiMem为构建适应性和自我进化的基于大语言模型的对话代理提供了一个原理性且可扩展的设计范式。代码可在https://github.com/jojopdq/HiMem上获得。

英文摘要:

Although long-term memory systems have made substantial progress in recent years, they still exhibit clear limitations in adaptability, scalability, and self-evolution under continuous interaction settings. Inspired by cognitive theories, we propose HiMem, a hierarchical long-term memory framework for long-horizon dialogues, designed to support memory construction, retrieval, and dynamic updating during sustained interactions. HiMem constructs cognitively consistent Episode Memory via a Topic-Aware Event--Surprise Dual-Channel Segmentation strategy, and builds Note Memory that captures stable knowledge through a multi-stage information extraction pipeline. These two memory types are semantically linked to form a hierarchical structure that bridges concrete interaction events and abstract knowledge, enabling efficient retrieval without sacrificing information fidelity. HiMem supports both hybrid and best-effort retrieval strategies to balance accuracy and efficiency, and incorporates conflict-aware Memory Reconsolidation to revise and supplement stored knowledge based on retrieval feedback. This design enables continual memory self-evolution over long-term use. Experimental results on long-horizon dialogue benchmarks demonstrate that HiMem consistently outperforms representative baselines in accuracy, consistency, and long-term reasoning, while maintaining favorable efficiency. Overall, HiMem provides a principled and scalable design paradigm for building adaptive and self-evolving LLM-based conversational agents. The code is available at https://github.com/jojopdq/HiMem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑