# 持续学习的范式转变：从参数中心到系统级适应

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-06 08:00
- AIHOT 分数：40
- AIHOT 链接：https://aihot.virxact.com/items/cmsirrsop1qorronkgkjuw0rg
- 原文链接：https://arxiv.org/abs/2608.06216

## AI 摘要

持续学习正从参数中心机制转向系统级适应，涵盖训练策略、架构设计及权重适配之外的更广范畴。该综述提出When、How、Where三维框架：How涵盖off-policy、on-policy与超越梯度的优化，When覆盖预训练至推理阶段，Where区分内部参数与外部结构约束，并系统梳理了代表性方法及未来挑战。

## 正文

Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architectural designs, and weight adaptation. However, emerging paradigms are reshaping the scope of CL beyond this traditional model adaptation view. For instance, on-policy learning broadens the space of update mechanisms; test-time training extends CL from the training phase to inference; and external harness components such as memory, skill libraries, and interaction protocols extend the evolutionary boundaries of model capabilities far beyond the static parameter space. Collectively, these developments indicate a transition from parameter-centric learning toward system-level adaptation. To characterize this transition, we examine the evolution of continual learning through three dimensions: When, How, and Where learning occurs. The How dimension encompasses off-policy, on-policy, and beyond-gradient optimization mechanics. The When dimension captures evolution across pre-training, post-training, and inference-time stages. The Where dimension delineates updates occurring within internal parameters versus external structural constraints. Anchored by this tri-axial framework, we systematically survey representative methods, trace the ongoing transition of continual learning, and discuss the key challenges, broader implications, and future directions arising from this paradigm shift.