AI 智能體的記憶中心持續學習
Memory-Centric Continual Learning for AI Agents
Memory-Centric Continual Learning(MCCL)提出以記憶推動 AI 智能體持續學習,並以記憶能否改善未來行動,而非只看能否檢索資訊,作為評估核心。框架以儲存基底、記憶資產和管理政策建立分類及雙迴路生命週期,並評估記憶保留、適應變化和任務遷移。它亦建構記憶擴展框架,分析經驗、儲存容量和運算預算與智能體表現的關係。
Published on Oct 21
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
Memory-Centric Continual Learning reframes agent memory as an active driver of behavioral improvement through a taxonomy of storage substrates, assets, and policies, a two-loop lifecycle, and scaling frameworks evaluated by retention, adaptation, and transfer.
Autonomous agents powered by foundation models can reason, plan, and use tools, but their fixed weights and context limits hinder sustained learning from experience over long-term deployment. While external memory systems attempt to bridge this gap, they mostly act as passive retrieval caches, evaluated primarily by whether they can recall stored facts or past interactions. Whether memory can drive genuine continual learning remains an open question. In this paper, we introduce Memory-Centric Continual Learning (MCCL), arguing that memory should be judged by whether it improves future actions, not merely what it retrieves. MCCL has three main parts. First, a three-axis taxonomy organizes memory by where state is stored (substrates), what form it takes (assets), and how it is managed (policies). This defines a two-loop lifecycle that updates memory state in an inner loop while refining management policies in an outer loop based on task feedback. Second, an evaluation protocol measures retention under interference, adaptation to change, and task transfer to isolate genuine behavioral gains from simple context expansion. Third, a memory scaling framework models how agent performance scales with experience, storage capacity, and compute budgets across non-parametric and parametric memory. Together, these components reframe agent memory from passive lookup to continuous learning, offering a principled route toward self-improving autonomous agents.
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2610.29357
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.29357 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.29357 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.29357 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co