并非所有记忆都平等：面向LLM智能体有效性感知检索的分层协作记忆
原标题：Not All Memories Are Equal: Hierarchical Collaborative Memory for Validity-Aware Retrieval in LLM Agents
AI 摘要
该论文提出 HiCoMER 框架，用于 LLM 智能体在团队协作场景下的分层协作记忆管理与有效性感知检索。现有记忆增强系统通常将所有记忆视为扁平池并按语义相关性、重要性或新近度排序，容易检索到语义相关但已过时或与团队共识冲突的个体记忆。HiCoMER 通过分层记忆冲突更新器、有效性感知记忆检索器和记忆锚定答案生成器三个组件，优先检索当前有效的记忆，并构建了两个新数据集验证其能减少过时检索、保持团队共识并提升下游问答质量。
正文节选
Not All Memories Are Equal: Hierarchical Collaborative Memory for Validity-Aware Retrieval in LLM Agents Abstract 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 seman