Catalog Systems Recent method papers — theorized, no distinct product CL of LLMs Survey

CL of LLMs Survey

https://dl.acm.org/doi/10.1145/3735633

Comprehensive survey. ACM Computing Surveys 2025. Anchor reference for the continual-learning-of-LLMs subfield.

Active · Verified 2026-10-23 · fresh as of 2026-10-23 · 19 cited facts, 0 with a third-party source · Suggest a correction

At a glance

Type
Continual learning of LLMs (survey) vendor fix
Tier
T3
Section
Recent method papers — theorized, no distinct product
Created
2024-04 vendor fix
Latest release
no releases fix
License
Unlicensed repo fix
GitHub
542★ repo fix
Pricing
not applicable — research paper fix
Funding
not applicable — not commercial fix
Freshness
2026-10-23 fix
Layer
agent-infra repo fix

Memory taxonomy

storage
parametric
retrieval
parametric-recall
persistence
parametric-permanent
update
parametric-edit
unit
weight
governance
opaque
conflict
training-time

When to use

Optimised for: not applicable - research paper

Anti-fit: not applicable - research paper

Pros & cons

Pros

Comprehensive survey of continual learning specifically for LLMs.

Cons

Survey-only; no new method; recommendations are general.

Claims & capabilities

Comprehensive survey of continual learning of LLMs covering vertical (general->specific) and horizontal (across time/domains) continuity; structured around Continual Pre-Training, Domain-Adaptive Pre-training, and Continual Fine-Tuning.

Technical surface

API surface
not applicable — research paper
Backend storage
not applicable — research paper
Deployment
not applicable — research paper
Embedding model
not applicable — research paper
Multi-tenancy
not applicable — research paper
MCP
not applicable — research paper, no deployed product
A2A
not applicable — research paper, no deployed product
OpenTelemetry
not applicable — research paper, no deployed product

Similar systems

Other recent method papers — theorized, no distinct product in the catalog, ranked by inbound references.

  • Compressive Transformer T3

    Maintains recent states in full resolution while compressing older memories with learned compression functions. DeepMind.

  • MemGPT v2 / agent-tools T3

    Already in catalog as the foundational MemGPT paper. Note: Letta is the productionised successor (cross-listed).

  • Transformer-XL T3

    Extends context through segment-level recurrence + caching of hidden states from prior segments. Foundational long-context architecture.

  • Generative Agents T3

    Park et al. — landmark agent-simulation paper. Reflection + memory stream + retrieval enable believable agent behavior.

  • MemoryBank T3

    Enhances LLMs with long-term memory. Early influential paper.

  • Reflexion T3

    Language agents with verbal reinforcement learning.

Sources (18 cited facts, 0 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

Related systems

References (2)