让记忆像网络一样动态演化，提升智能体在复杂任务中的适应能力
Rethinking Memory as Continuously Evolving Connectivity
- 将记忆建模为异构图，通过三阶段逐步优化连接结构
- 在三个基准上达到最优表现，显著提升任务泛化与长期适应性
- 适合研究动态记忆、智能体系统或复杂任务规划的开发者
现有增强记忆的大模型智能体通常将记忆视为静态存储，具有预定义表征和固定检索流程，在动态环境中容易失效。针对这一问题，我们提出FluxMem——一种连接关系持续演化的记忆框架，将记忆建模为异构图，并通过初始连接构建、反馈驱动优化、长期巩固三个阶段逐步完善拓扑结构。执行过程中，FluxMem能修复缺失链接、剔除干扰信息、对齐抽象粒度，并将重复成功的任务路径提炼为可复用的过程电路，由统一的通用性与演化成熟度指标引导。在LoCoMo、Mind2Web和GAIA三个本质不同的基准上，FluxMem均实现一致的领先性能，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。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。