从他人处学习，为你而行动：面向LLM智能体的跨用户记忆共享
Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents
浏览论文内容
中文总结 AI 辅助
针对LLM智能体跨用户经验共享中的偏好冲突问题，提出ShareMem记忆架构，通过两阶段整合和范围优先检索实现经验共享与用户偏好绑定，在多个任务上优于用户本地记忆。
中文摘要 AI 辅助
服务于不同用户的大型语言模型（LLM）智能体经常解决相关任务，然而，各用户独立的历史记录可能使得可复用的经验对其他智能体不可及。汇集记忆扩大了访问范围，但存在转移与接收用户需求相冲突的偏好的风险。我们提出ShareMem，一种记忆架构，它在共享可复用经验的同时，将经验的应用植根于接收用户自身的偏好。共享经验指示如何行动以及应参考哪些偏好；接收用户的记忆则提供其具体的偏好值。两阶段整合先在本地精炼经验，再将接受的编辑整合进共享池。在执行阶段，范围优先的检索在共同的条目预算下联合选择本地和共享经验，而用户绑定通道支持初始和智能体发起的偏好检索。我们在网页导航（Mind2Web）、在线个性化交互（VitaBench~2.0）和多会话编码（MemoryCode）上，使用四种骨干模型评估ShareMem。与匹配的用户本地记忆相比，它在所有四种模型上分别提高了步骤成功率、平均任务成功率和对话宏编码分数。消融实验支持两阶段整合，因其带来更小的共享池、更低的归纳令牌使用量和更好的下游性能，并支持经验指导与主动偏好检索之间的互补性。进一步分析表明，当相关本地经验稀缺时，共享帮助最大，而来源质量和跨用户偏好干扰限制了有效转移。
英文摘要
Large language model (LLM) agents serving different users often solve related tasks, yet separate user histories can leave reusable experience inaccessible to other agents. Pooling memories expands access but risks transferring preferences that conflict with the receiving user's requirements. We introduce ShareMem, a memory architecture that shares reusable experience while grounding its application in the receiving user's own preferences. Shared experiences indicate how to act and which preferences to consult; the receiving user's memory supplies their concrete values. Two-stage consolidation refines experience locally before integrating accepted edits into a shared pool. During execution, scope-first retrieval jointly selects local and shared experiences under a common entry budget, while a user-bound channel supports initial and agent-initiated preference retrieval. We evaluate ShareMem across web navigation (Mind2Web), online personalized interaction (VitaBench~2.0), and multi-session coding (MemoryCode) with four backbone models. It improves step success, average task success, and dialogue-macro coding scores, respectively, over matched user-local memory across all four models. Ablations favor two-stage consolidation for smaller shared pools, lower induction token usage, and better downstream performance, and support complementarity between experience guidance and active preference retrieval. Further analyses show that sharing helps most when relevant local experience is scarce, while source quality and cross-user preference interference limit useful transfer.
