Large language model (LLM) agents are increasingly equipped with memory, which are stored experience and reusable guidance that can improve task-solving performance. Recent \emph{self-evolving} systems update memory based on interaction outcomes, but most existing evolution pipelines are developed for static train/test splits and only approximate online learning by folding static benchmarks, making them brittle under true distribution shift and continuous feedback. We introduce \textsc{Live-Evo}, an online self-evolving memory system that learns from a stream of incoming data over time. \textsc{Live-Evo} decouples \emph{what happened} from \emph{how to use it} via an Experience Bank and a Meta-Guideline Bank, compiling task-adaptive guidelines from retrieved experiences for each task. To manage memory online, \textsc{Live-Evo} maintains experience weights and updates them from feedback: experiences that consistently help are reinforced and retrieved more often, while misleading or stale experiences are down-weighted and gradually forgotten, analogous to reinforcement and decay in human memory. On the live \textit{Prophet Arena} benchmark over a 10-week horizon, \textsc{Live-Evo} improves Brier score by 20.8\% and increases market returns by 12.9\%, while also transferring to deep-research benchmarks with consistent gains over strong baselines. Our code is available at https://github.com/ag2ai/Live-Evo.

翻译：大型语言模型（LLM）智能体日益配备记忆功能，即存储的经验和可复用的指导，以提升任务解决性能。近期的**自演化**系统基于交互结果更新记忆，但现有演化流程大多针对静态训练/测试集开发，仅通过折叠静态基准来近似在线学习，使其在真实分布偏移和持续反馈下表现脆弱。我们提出 \textsc{Live-Evo}，一种在线自演化记忆系统，能够随时间从持续流入的数据流中学习。\textsc{Live-Evo} 通过经验库和元指导库将**已发生事件**与**如何利用经验**解耦，为每项任务从检索到的经验中编译任务自适应指导。为实现在线记忆管理，\textsc{Live-Evo} 维护经验权重并根据反馈更新：持续提供帮助的经验会被强化并更频繁检索，而产生误导或过时的经验则被降权并逐渐遗忘，类似于人类记忆中的强化与衰减机制。在为期10周的实时 \textit{Prophet Arena} 基准测试中，\textsc{Live-Evo} 将 Brier 分数提升20.8\%，市场回报率提高12.9\%，同时迁移至深度研究基准时亦能持续超越强基线模型。代码已发布于 https://github.com/ag2ai/Live-Evo。