General continual learning (GCL) challenges intelligent systems to learn from single-pass, non-stationary data streams without clear task boundaries. While recent advances in continual parameter-efficient tuning (PET) of pretrained models show promise, they typically rely on multiple training epochs and explicit task cues, limiting their effectiveness in GCL scenarios. Moreover, existing methods often lack targeted design and fail to address two fundamental challenges in continual PET: how to allocate expert parameters to evolving data distributions, and how to improve their representational capacity under limited supervision. Inspired by the fruit fly's hierarchical memory system characterized by sparse expansion and modular ensembles, we propose FlyPrompt, a brain-inspired framework that decomposes GCL into two subproblems: expert routing and expert competence improvement. FlyPrompt introduces a randomly expanded analytic router for instance-level expert activation and a temporal ensemble of output heads to dynamically adapt decision boundaries over time. Extensive theoretical and empirical evaluations demonstrate FlyPrompt's superior performance, achieving up to 11.23%, 12.43%, and 7.62% gains over state-of-the-art baselines on CIFAR-100, ImageNet-R, and CUB-200, respectively. Our source code is available at https://github.com/AnAppleCore/FlyGCL.

翻译：通用持续学习（GCL）要求智能系统能够从单次遍历、非平稳且无明确任务边界的数据流中持续学习。尽管近期基于预训练模型的持续参数高效调优（PET）方法展现出潜力，但这些方法通常依赖多轮训练周期和显式的任务提示，限制了其在GCL场景中的有效性。此外，现有方法往往缺乏针对性设计，未能解决持续PET中的两个核心挑战：如何将专家参数分配给持续演化的数据分布，以及如何在有限监督下提升其表征能力。受果蝇具有稀疏扩展与模块化集成特性的层次化记忆系统启发，我们提出FlyPrompt——一个脑启发式框架，将GCL分解为两个子问题：专家路由与专家能力提升。FlyPrompt引入了随机扩展的解析路由器以实现实例级专家激活，并采用输出头的时间集成机制来动态调整随时间演化的决策边界。大量理论与实验评估表明，FlyPrompt在CIFAR-100、ImageNet-R和CUB-200数据集上分别以11.23%、12.43%和7.62%的显著优势超越现有先进基线方法。源代码已发布于https://github.com/AnAppleCore/FlyGCL。