MemBART

Preserves memory states across dialogue turns for coherent long-term interactions. (Cited in survey but the paper's exact arxiv/venue identifier was not recoverable in a quick search — likely a less-prominent dialogue-systems paper.)

At a glance

Type
Memory states across dialogue turns
Tier
T4
Created
2025-08
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
not applicable — not commercial
Funding
not applicable — not commercial

Taxonomy

storage
kv-cache
retrieval
attention
persistence
long-term
update
overwrite
unit
kv-token
governance
opaque
conflict
n/a

When to use

Optimised for: not applicable - research paper

Anti-fit: not applicable - research paper

Pros & cons

Pros

Preserves memory states across dialogue turns for coherent long-term interactions.

Cons

Pre-LLM era; less informative than modern memory-tuned approaches.

Claims & capabilities

Stateful memory-augmented BART for efficient dialogue modeling; separate memory module alongside pre-trained transformer for state/context exchange. Headline: superior efficiency and performance vs. pre-trained Transformer baselines (no specific headline metric in abstract); baseline: vanilla BART and pre-trained Transformer baselines; primary datasets: 3 dialogue datasets and 2 language-modeling datasets.

Technical surface

API surface
not applicable — research paper
Backend storage
not applicable — research paper
Deployment
not applicable — not a deployable product
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.

Related systems

References (20)

Referenced by (1)

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.