Continual Learning in Transition

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Zhiyan Hou, Dan Zhang, Tao Feng, Liyuan Wang, Wei Li, Xiangzhao Hao, Hongyan An, Junfeng Fang, Haokai Ma, Zhaohui Xu, Haiyun Guo, Jinqiao Wang, Tat-Seng Chua
• Venue: arXiv: cs.LG
• Published: 2026-08-06
• Collected: 2026-08-07
• URL: http://arxiv.org/abs/2608.06216v1
• PDF: https://arxiv.org/pdf/2608.06216v1
• DOI: UNKNOWN

Plain-Language Brief

The authors explore the evolution of continual learning (CL) in a tri-axial framework: When, How, and Where learning occurs. They discuss how CL is transitioning from parameter-centric learning to system-level adaptation, highlighting developments such as on-policy learning, test-time training, and external harness components.

What the Document Says

• The authors examine the evolution of continual learning through three dimensions: When, How, and Where learning occurs.
• The How dimension includes 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.
• They discuss the transition of continual learning from parameter-centric learning to system-level adaptation.
• Representative methods are surveyed, and key challenges, broader implications, and future directions arising from this paradigm shift are discussed.

Key Concepts Mentioned

• continual learning
• parameter-centric learning
• system-level adaptation
• off-policy learning
• on-policy learning
• beyond-gradient optimization
• pre-training
• post-training
• inference-time

Claims Made by the Document

• Continual learning is transitioning from parameter-centric learning to system-level adaptation.

Evidence Used

• The authors discuss the developments in continual learning that indicate this transition, such as on-policy learning, test-time training, and external harness components.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.