CREATOR
Tool creation for disentangling abstract and concrete reasoning. EMNLP Findings.
At a glance
- Type
- Tool creation for reasoning
- Tier
- T3
- Created
- 2023-05-23 (arxiv 2305.14318 submitted May 23 2023; EMNLP 2023 Findings)
- 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
- skill
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: not applicable - research paper
Anti-fit: not applicable - research paper
Pros & cons
Pros
Tool creation for disentangling abstract and concrete reasoning; EMNLP Findings.
Cons
Created tools quality varies; tool reuse across domains is brittle.
Claims & capabilities
Disentangles abstract tool creation and concrete decision execution; LLMs autonomously generate custom tools using documentation and code. Headline: 59.7% on MATH, 94.7% on TabMWP, 75.5% on the new Creation Challenge; baselines: chain-of-thought, program-of-thought (with/without rectification), tool-use (WolframAlpha API); primary datasets: MATH, TabMWP, and the introduced Creation Challenge (~2K problems).
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.