The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has shifted from simple context extension to the development of dedicated agentic memory systems. However, existing approaches typically rely on rigid retrieval granularity, accumulation-heavy maintenance strategies, and coarse-grained update mechanisms. These design choices create a persistent mismatch between stored information and task-specific reasoning demands, while leading to the unchecked accumulation of logical inconsistencies over time. To address these challenges, we propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities. AMA employs a hierarchical memory design that dynamically aligns retrieval granularity with task complexity. Specifically, the Constructor and Retriever jointly enable multi-granularity memory construction and adaptive query routing. The Judge verifies the relevance and consistency of retrieved content, triggering iterative retrieval when evidence is insufficient or invoking the Refresher upon detecting logical conflicts. The Refresher then enforces memory consistency by performing targeted updates or removing outdated entries. Extensive experiments on challenging long-context benchmarks show that AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods, demonstrating its effectiveness in maintaining retrieval precision and long-term memory consistency.

翻译：大型语言模型（LLM）智能体的快速发展对鲁棒的记忆系统提出了迫切需求，以支持长期连贯的交互和复杂推理。得益于LLM的强大能力，近期研究重点已从简单的上下文扩展转向专用智能体记忆系统的开发。然而，现有方法通常依赖于固定的检索粒度、累积密集的维护策略和粗粒度的更新机制。这些设计选择导致存储信息与任务特定推理需求之间持续失配，同时随时间推移引发逻辑不一致性的无约束累积。为应对这些挑战，我们提出基于多智能体协作的自适应记忆框架（AMA），该新颖框架通过协同智能体实现多粒度记忆管理。AMA采用分层记忆设计，动态对齐检索粒度与任务复杂度。具体而言，构造器与检索器协同实现多粒度记忆构建与自适应查询路由。判定器验证检索内容的相关性与一致性，在证据不足时触发迭代检索或在检测到逻辑冲突时调用刷新器。刷新器随后通过执行定向更新或移除过时条目来强制保证记忆一致性。在具有挑战性的长上下文基准测试上的大量实验表明，AMA显著优于现有最优基线方法，同时相比全上下文方法减少约80%的令牌消耗，验证了其在保持检索精度与长期记忆一致性方面的有效性。