# 将记忆视为持续演化的连接性

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-27 08:00
- AIHOT 分数：63
- AIHOT 链接：https://aihot.virxact.com/items/cmpp1ycod0b51slv4d9tsgc1g
- 原文链接：https://arxiv.org/abs/2605.28773

## AI 摘要

现有记忆增强大语言模型智能体常将记忆视为静态存储，这在动态环境中较为脆弱。为此，FluxMem框架提出将记忆建模为异构图，并通过初始连接形成、反馈驱动细化和长期巩固三个阶段，持续优化其拓扑结构。在执行时，该框架能修复缺失连接、剪除干扰、对齐抽象粒度，并将反复成功的轨迹蒸馏为可复用的程序化回路。在LoCoMo、Mind2Web和GAIA三个基准测试上，FluxMem均达到了SOTA水平，展现出在复杂智能体环境中强大的适应与泛化能力。代码将开源于GitHub。

## 正文

Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variation, and heterogeneous signals continuously reshape what should be remembered and how it should be connected. To address this, we propose FluxMem, a connectivity-evolving memory framework that models memory as a heterogeneous graph and progressively refines its topology through three stages: initial connection formation, feedback-driven refinement, and long-term consolidation. During execution, FluxMem repairs missing links, prunes interference, aligns abstraction granularity, and distills recurrent successful trajectories into reusable procedural circuits, guided by one metric for memory generalizability and evolutionary maturity. Across three fundamentally distinct benchmarks including LoCoMo, Mind2Web, and GAIA, FluxMem achieves consistent state-of-the-art performance, demonstrating strong adaptation and generalization in complex agentic environments. The code will be open-sourced in https://github.com/zjunlp/LightMem.