重新思考記憶作為持續演變的連結性

摘要

现有基于记忆增强的大语言模型智能体通常将记忆视为静态存储库，采用预定义表示和固定检索流程，在动态智能体环境中显得脆弱——其中反馈、任务变化及异构信号持续重塑应被记住的内容及其连接方式。为解决这一问题，我们提出FluxMem——一种连接进化型记忆框架，将记忆建模为异质图，并通过三个阶段逐步优化其拓扑结构：初始连接生成、反馈驱动优化及长期巩固。在执行过程中，FluxMem修复缺失连接、剪除干扰信息、对齐抽象粒度，并将重复成功的轨迹提炼为可复用的程序化回路，以记忆泛化性与进化成熟度作为统一评估指标。在LoCoMo、Mind2Web及GAIA三个截然不同的基准测试中，FluxMem均取得稳定最优性能，展现出在复杂智能体环境中的强大适应与泛化能力。代码将在https://github.com/zjunlp/LightMem开源。

English

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.