发表机构
Southern University of Science and Technology; Tsinghua University; Deepexi Technology Co. Ltd.（南方科技大学; 清华大学; 深度求索科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ROAM提出关系引导的原子记忆管理框架，通过分类原子关系并组织主次视图，提升长期智能体回答准确率最高达29.8个百分点。
AI 中文摘要
长期语言模型智能体依赖跨交互的外部记忆。原子记忆尤其有用：其细粒度的语义边界能够实现精确检索和观察之间的直接比较。然而，累积的原子不可避免地变得冗余、重叠或冲突。现有方法通常要求LLM管理器直接添加、更新、删除或重写记忆，将语义解释、存储决策和内容生成耦合在一次易出错的操作中。我们提出ROAM，一个关系引导的框架，利用原子性进行管理，同时允许更丰富的回答时表示。ROAM将传入-存储的原子对分类为独立、等价、方向性包含或冲突，然后将观察组织为主动的Primary角色和支持性的Evidence角色。融合随后将互补细节和时间变化组合成紧凑的、可能非原子的视图。仅检索Primary视图用于回答，防止冗余或过时的原子独立竞争。跨模型和评估设置，ROAM将回答准确率提升高达29.8个百分点。消融实验显示不同关系的互补益处以及融合在角色组织之外的一致增益。机制分析进一步发现回答关键源召回率提高15.6个百分点，混淆令牌占比降低11.5个百分点。ROAM在管理器规模变化下保持鲁棒。
英文摘要
Long-term language-model agents rely on external memory across interactions. Atomic memories are particularly useful: their fine-grained semantic boundaries enable precise retrieval and direct comparison between observations. Yet accumulating atoms inevitably become redundant, overlapping, or conflicting. Existing methods often ask an LLM manager to add, update, delete, or rewrite memories directly, coupling semantic interpretation, storage decisions, and content generation in one error-prone operation. We introduce ROAM, a relation-guided framework that uses atomicity for management while allowing richer answer-time representations. ROAM classifies incoming--stored atom pairs as independent, equivalent, directionally subsuming, or conflicting, then organizes observations into active Primary and supporting Evidence roles. Fusion subsequently combines complementary details and temporal changes into compact, potentially non-atomic views. Only Primary views are retrieved for answering, preventing redundant or outdated atoms from competing independently. Across models and evaluation settings, ROAM improves answer accuracy by up to 29.8 percentage points. Ablations show complementary benefits from different relations and consistent gains from fusion beyond role organization. Mechanism analysis further finds 15.6-point higher answer-critical source recall and an 11.5-point lower confounder-token share. ROAM remains robust across manager scales.
Comments21 pages, 4 figures, 10 tables
