AI Pulse
📄 论文解读

AI 学到的经验,该给谁看?

多个 AI 智能体一起「长本事」时,最容易忽略一件事:一条经验该给谁用、哪些内容不能外泄。MixUA 把每次用户和智能体交互的轨迹提炼成「经验」,再按受益者和可披露范围,把它归到某个用户-智能体配对、某个用户、某个智能体或全局。配套的 CrossLearnBench 用五个用户、七个智能体测:通过率比无记忆高最多 16 个百分点,比单一全局记忆高 5 个点,连别人在别的智能体上试过的任务也能受益;此前说过的偏好能记住九成,而植入的隐私事实被探针在禁读范围里找到的比例最多 0.02%。它不是你明天能用上的东西,但指向一个用户和智能体共同进化的全局系统。

📄 原文摘要(英文)

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.

arXiv 原文

订阅 AI Pulse

每天 08:00 · 12:30 · 18:30 · 23:50 更新