Paper page - Memory-Centric Continual Learning for AI Agents

Source: https://huggingface.co/papers/2610.29357 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 introduceMemory-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, athree-axis taxonomyorganizes memory by where state is stored (substrates), what form it takes (assets), and how it is managed (policies). This defines atwo-loop lifecyclethat updates memory state in an inner loop while refining managementpoliciesin an outer loop based on task feedback. Second, an evaluation protocol measuresretention under interference,adaptation to change, andtask transferto isolate genuine behavioral gains from simple context expansion. Third, amemory scaling frameworkmodels how agent performance scales with experience, storage capacity, and compute budgets across non-parametric andparametric memory. Together, these components reframe agent memory from passive lookup to continuous learning, offering a principled route toward self-improving autonomous agents.

View arXiv pageView PDFAdd 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 paper0

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 paper0

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 paper0

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 paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.