FluxMem 把智能体记忆从静态存储升级为动态拓扑，解决了长期任务中记忆碎片化和干扰问题。做智能体系统或记忆建模的团队值得看看这个新范式，可以直接参考其论文思路。
FluxMem 提出将智能体记忆视为异构图不断演化的拓扑结构，而非传统存储。其工作流程分为三个阶段：初始连接形成、反馈驱动优化、以及将成功路径固化为可复用程序回路。执行时能自动修复缺失链接、剪枝干扰并调整抽象粒度。该方法在 LoCoMo、Mind2Web 和 GAIA 三个不同记忆场景下均达到当前最优。论文已公开，适合关注智能体记忆架构的研究者和开发者。
// Memory as Connectivity // One of the cleaner reframings of agent memory I have seen this month. ...
// Memory as Connectivity // One of the cleaner reframings of agent memory I have seen this month. FluxMem treats memory as the continuously evolving topology of a heterogeneous graph. Three stages run together: initial connection formation, feedback-driven refinement, and long-term consolidation of recurrent successful trajectories into reusable procedural circuits. During execution, it repairs missing links, prunes interference, and aligns abstraction granularity. SOTA on LoCoMo, Mind2Web, and GAIA across three distinct memory regimes. Paper: arxiv.org/abs/2605.28773 Learn to build effective AI agents in our academy: academy.dair.ai 💬 1 🔄 5 ❤️ 20 👀 945 📊 6 ⚡
- arXiv cs.AI05-27 17:35原文