发表机构
Nanyang Technological University; University of Macau; Worcester Polytechnic Institute; Zhejiang University（南洋理工大学; 澳门大学; 伍斯特理工学院; 浙江大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对LLM智能体协作中记忆过时与冲突问题，提出HiCoMER框架，通过层级冲突更新与有效性感知检索，优先使用有效记忆，提升问答质量。
AI 中文摘要
在团队协作场景中，记忆是异构且持续演变的。团队记忆捕捉集体决策、协议和当前共识，而个体记忆则保留成员特有的观察、执行轨迹和中间进展。现有的记忆增强系统通常将所有存储的记忆视为一个平坦的池子进行检索，仅根据语义相关性、重要性或新近度进行排序，而不对层级结构或演变中的有效性进行建模。因此，它们常常浮现出语义相关但过时或冲突的记忆，尤其是那些不再与当前团队共识一致的个体记忆，而不是优先考虑当前有效的记忆。当协作式LLM智能体回答用户问题时，这一问题尤为突出，因为其回答应基于有效的记忆。我们提出HiCoMER，一个用于LLM智能体中层级协作记忆管理和有效性感知检索的框架。HiCoMER首先维护团队和个体记忆的有效性，然后检索仍然有效的记忆，而非直接从所有存储的记忆中检索。它包含三个组件：层级记忆冲突更新器、有效性感知记忆检索器和基于记忆的答案生成器。为评估HiCoMER，我们构建了两个新的数据集，用于协作场景中基于记忆的问答。在两个数据集上的实验表明，HiCoMER通过减少过时检索、保持当前团队共识并提升下游问答质量，持续优于强基线方法。
英文摘要
In team collaboration scenarios, memory is heterogeneous and continually evolving. Team memories capture collective decisions, protocols, and current consensus, while individual memories preserve member-specific observations, execution traces, and intermediate progress. Existing memory-augmented systems typically retrieve from all stored memories as a flat pool, ranking them by semantic relevance, importance, or recency without modeling hierarchical structure or evolving validity. As a result, they often surface semantically relevant but outdated or conflicting memories, especially individual memories that no longer align with current team consensus, instead of prioritizing currently valid memories. This is particularly problematic when collaborative LLM agents answer user questions, since their responses should be grounded in valid memories. We propose HiCoMER, a framework for hierarchical collaborative memory management and validity-aware retrieval in LLM agents. HiCoMER first maintains the validity of team and individual memories and then retrieves memories that remain valid, rather than retrieving directly from all stored memories. It consists of three components: a Hierarchical Memory Conflict Updater, a Validity-Aware Memory Retriever, and a Memory-Grounded Answer Generator. To evaluate HiCoMER, we construct two new datasets for memory-grounded question answering in collaborative settings. Experiments on both datasets show that HiCoMER consistently outperforms strong baselines by reducing outdated retrieval, preserving current team consensus, and improving downstream QA quality.
