受大脑启发的内存机制，让智能体长期任务更稳定可靠。
CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems
- 用目标感知门控和效用标记，分阶段管理短期与长期记忆
- 在噪声干扰下性能下降比基线少40%以上，长期记忆更稳定
- 适合需要持续记忆的复杂长流程智能体系统
大型语言模型代理在长时间运行的任务中需持续保存用户与任务状态。现有记忆系统多采用外部数据库式的随意读写规则，易导致记忆不稳、整合不足且易受干扰内容影响。本文提出CraniMem，一种受颅脑神经认知启发的门控与有界多阶段记忆设计。该系统结合目标条件门控与效用标记，利用有界情景缓冲区维持短期连续性，通过结构化长期知识图谱实现持久语义召回。定期合并循环将高价值记忆轨迹复现至图谱，同时清除低价值项，控制记忆增长并减少干扰。在清洁输入与注入噪声的长周期基准测试中，CraniMem优于基础RAG与Mem0基线，表现出更小的性能下降。代码已开源于https://github.com/PearlMody05/Cranimem，配套PyPI包为cranimem。
原文摘要 · Abstract (English)
Large language model (LLM) agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns. Many existing agent memory systems behave like external databases with ad hoc read/write rules, which can yield unstable retention, limited consolidation, and vulnerability to distractor content. We present CraniMem, a neurocognitively motivated, gated and bounded multi-stage memory design for agentic systems. CraniMem couples goal conditioned gating and utility tagging with a bounded episodic buffer for near term continuity and a structured long-term knowledge graph for durable semantic recall. A scheduled consolidation loop replays high utility traces into the graph while pruning low utility items, keeping memory growth in check and reducing interference. On long horizon benchmarks evaluated under both clean inputs and injected noise, CraniMem is more robust than a Vanilla RAG and Mem0 baseline and exhibits smaller performance drops under distraction. Our code is available at https://github.com/PearlMody05/Cranimem and the accompanying PyPI package at https://pypi.org/project/cranimem.
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。