JARVIS-1
Open-world multi-task agents with memory-augmented multimodal LLMs. TPAMI 2024 . (Distinct from any other JARVIS.)
At a glance
- Type
- Open-world memory-augmented agents
- Tier
- T3
- Created
- 2023-11
- 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
- vector
- retrieval
- similarity
- persistence
- cross-session
- update
- extraction
- unit
- episode
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: not applicable - research paper
Anti-fit: not applicable - research paper
Pros & cons
Pros
Open-world multi-task agents with memory-augmented multimodal LLMs; TPAMI 2024.
Cons
Minecraft / open-world scope; cross-domain transfer not demonstrated.
Claims & capabilities
Open-world Minecraft agent combining multimodal LM with memory of pre-trained knowledge and game survival; completes 200+ tasks. Headline: 12.5% on ObtainDiamondPickaxe in 60 minutes — 5x SOTA reliability (vs. VPT at 2.5% in 20min, DEPS ~2.42%); baselines: GPT-based planning, ReAct, Inner Monologue, DEPS, VPT; primary dataset: 200+ Minecraft Universe Benchmark tasks across 11 task groups.
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 (1)
- Voyager cites — S2 isInfluential citation