Databricks 推出 MemCurrent 持久记忆架构，智能体可跨会话记住上下文
Databricks 发了个智能体记忆架构 MemCurrent，内部基准上通过率翻三倍、token 省三成，做 Agent 的可以看看思路。
Databricks 发布 MemCurrent，一种面向生产环境智能体的持久记忆架构，结合情景记忆与派生记忆，提供插件自动记录上下文、智能体按需调用工具、后台离线 consolidation 流水线三种访问模式。智能体因此可跨会话保留用户偏好、历史修正、指标定义和成功工作流。在基于真实企业数据构建的内部基准上，智能体通过率提升至三倍，token 消耗减少 31%，运行速度加快 26%。该架构已集成到 Agent Bricks 的 Memory 产品中，并支撑 Genie 的记忆功能。
Introducing MemCurrent, a persistent memory architecture designed to help production agents stop starting from zero.
MemCurrent combines episodic memory with derived memory across three access patterns:
• Plugins to log and load context automatically • Tools the agent calls on demand • An offline “dreaming” pipeline that consolidates memory in the background
Agents carry forward user preferences, prior corrections, metric definitions and successful workflows instead of rediscovering them every session.
On our internal benchmark built from real enterprise data, MemCurrent triples the agent's pass rate while using 31% fewer tokens and running 26% faster. It's built into Agent Bricks' Memory offering and already powers memory in Genie.
Read the research: https://t.co/AYGXOqrhkO
