MixUA 记忆系统：按用户、智能体与全局四级粒度共享经验教训
Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction
做多用户 Agent 产品的人该看看这篇。它给记忆系统加了个权限维度：哪些经验只有这个用户能用，哪些可以全局共享，还附带基准 CrossLearnBench 专门测隐私泄漏，比常见的全局记忆方案干净不少。
arXiv 论文《Who Remembers What?》提出 MixUA 记忆系统，解决多用户、多智能体环境下经验共享的权限问题。它将独立的用户-智能体交互轨迹蒸馏为可复用的 lessons，并把每条 lesson 分配到用户-智能体对、用户、智能体或全局四种作用域之一，依据是这条经验对谁有用、可能泄露什么信息。
配套发布的 CrossLearnBench 混合基准，将既有智能体任务与用户偏好、隐私探针结合，专门测试私密信息是否会泄漏到其他用户可读的记忆中。实验设置包含 5 个用户和 7 个智能体，MixUA 相比无记忆方案 pass rate 最高提升 16 个百分点，相比单一全局记忆提升 5 个百分点，且任务可以是其他用户在其他智能体上才试过的。
偏好保留率最高达 90%，隐私探针中最多只有 0.02% 的测试在禁止作用域内发现被植入的私密事实。这组数字说明：按粒度隔离记忆不仅没有损失跨用户学习能力，还同时守住了隐私边界，比全局共享记忆和完全独立记忆两个极端都更有效。
Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction
Self-evolving agents improve their own skills, memory, and harness code from experience without retraining the base LLM, and group-evolving agents go further by sharing these lessons across agents. Yet most such systems overlook that sharing across users and heterogeneous agents requires deciding who can benefit from each lesson and what information must remain private. We present MixUA, a memory system that distills independent user-agent trajectories into lessons and assigns each lesson to a user-agent pair, user, agent, or global scope according to whom it benefits and what it may disclose. For evaluation, we introduce CrossLearnBench, a mixed-user-agent benchmark that pairs established agent tasks with user preferences and privacy probes that test whether private facts leak into memory other users can read. With five users and seven agents, MixUA raises pass rates by up to 16 points over no memory and 5 over a single global memory, even on tasks previously tried only by other users on other agents. It retains up to 90% of previously stated preferences, and at most 0.02% of privacy probes find a planted private fact in a forbidden scope. We hope MixUA offers a scalable path toward a global system where users and agents co-evolve.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include MixUA, CrossLearnBench, 智能体, 记忆系统.
Source attribution: curated from arXiv cs.LG (@Yunzhe Wang, Mesut Erhan Unal, Sheng Zhang, Shabnam Ghadar, Peng Tang).