Agent Workflow Memory
https://openreview.net/forum?id=NTAhi2JEEE
Workflow-based memory framework component.
At a glance
- Type
- Workflow as memory
- Tier
- T3
- Created
- 2024-09
- 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
- file
- retrieval
- injection
- persistence
- cross-session
- update
- extraction
- unit
- skill
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: not applicable - research paper
Anti-fit: not applicable - research paper
Pros & cons
Pros
Workflow-pattern abstraction means agents recall multi-step procedures, not just facts.
Cons
Workflow-shaped scope; less applicable to free-form recall.
Claims & capabilities
Induces commonly-reused workflows from past experiences and applies them in offline (training) and online (test-time) modes. Headline: +24.6% on Mind2Web and +51.1% relative success-rate on WebArena over baseline; baseline: BrowserGym autonomous agent without human-annotated workflows; primary datasets: Mind2Web and WebArena (812 tasks across 5 websites).
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
Referenced by (2)
- Inducing Programmatic Skills cites — S2 isInfluential citation
- ReasoningBank cites — S2 isInfluential citation