Catalog Systems Research / specialised systems EVOLVE-MEM

EVOLVE-MEM

https://openreview.net/forum?id=dfPQrg1WA5

Dynamic Memory Network + Hierarchical Memory Manager + Self-Improvement Engine. L0 raw embeddings, L1 contextual summaries, L2 high-level principles. NeurIPS 2025 (Scaling Environments for Agents workshop).

Active · Verified 2026-05-14 · fresh as of 2026-05-14 · 18 cited facts, 0 with a third-party source · Suggest a correction

At a glance

Type
Self-adaptive 3-level hierarchy vendor fix
Tier
T3
Section
Research / specialised systems
Created
searched not found fix
Latest release
not applicable — not OSS fix
License
not applicable — not OSS fix
GitHub
not applicable — no GitHub repo fix
Pricing
not applicable — not commercial fix
Funding
not applicable — not commercial fix
Freshness
2026-05-14 fix
Layer
agent-infra repo fix

Memory taxonomy

storage
hybrid
retrieval
similarity
persistence
long-term
update
consolidation
unit
summary
governance
opaque
conflict
llm-arbitrate

When to use

Optimised for: research positioning (see memory_model)

Anti-fit: not applicable - research paper

Pros & cons

Pros

Evolutionary memory pruning — explicit fitness function for what to keep.

Cons

Research-stage; no production deployments; eval coverage limited.

Claims & capabilities

58.3% overall accuracy on LoCoMo (claims SOTA across five reasoning categories).

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 research / specialised systems in the catalog, ranked by inbound references.

  • A-MEM T3

    Treats memories as atomic linkable notes — explicit nod to Zettelkasten knowledge management. Dynamic linking; retroactive memory revision.

  • BAI-LAB MemoryOS T3

    Hierarchical "OS" with Storage / Updating / Retrieval / Generation modules. Short-term → mid-term via FIFO dialogue-chain; mid-term → long-term via segmented paging.

  • Titans (Google) T4

    Neural long-term memory module that learns to memorise at test time. Uses gradient-of-loss as "surprise" signal; adaptive weight-decay forgetting. Three variants: MAC (memory-as-context), MAG (memory-as-gate), MAL (memory-as-layer).

  • EverMemOS T4

    Self-organizing memory OS for structured long-horizon reasoning. Three-phase model: episodic, semantic, reconstructive.

  • LiCoMemory T4

    Lightweight hierarchical graph (CogniGraph) with entities and relations as semantic indexing layers. Incremental graph construction, fast updates, low-latency inference. Nov 2025.

  • MemoRAG T3

    RAG framework on top of a long-context memory model. Builds global memory once, generates contextual clues at query time. TheWebConf 2025.

Sources (17 cited facts, 0 third-party)

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