CDMem
https://aclanthology.org/2025.naacl-industry.80/
Context-Dependent Memory framework. Three-stage encoding (expert / short-term / long-term) + graph-structured context-dependent indexing. NAACL 2025 Industry.
At a glance
- Type
- 3-stage encoding + graph indexing
- Tier
- T3
- Created
- searched not found
- 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
- graph
- retrieval
- graph-traversal
- persistence
- session
- update
- extraction
- unit
- chunk
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: not applicable - research paper
Anti-fit: not applicable - research paper
Pros & cons
Pros
Cross-domain memory sharing — agents transfer learned memory across tasks.
Cons
Research-stage; cross-domain transfer brittle.
Claims & capabilities
Cognitive psychology-inspired memory module for embodied agents. Headline: 85.8% success on ALFWorld and 56.0% on ScienceWorld, surpassing SOTA online LLM-centric approaches; baselines: SOTA online LLM-centric approaches; primary datasets: ALFWorld, ScienceWorld.
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.