{"id":"creator","name":"CREATOR","url":null,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/creator","family":"memory-research","section":"Recent method papers — theorized, no distinct product","sections":["Recent method papers — theorized, no distinct product"],"tier":3,"last_verified_at":"2026-10-28","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":{"storage":[{"value":"vector","primary":true,"reason":null}],"retrieval":[{"value":"similarity","primary":true,"reason":null}],"persistence":[{"value":"cross-session","primary":true,"reason":null}],"update":[{"value":"extraction","primary":true,"reason":null}],"unit":[{"value":"skill","primary":true,"reason":null}],"governance":[{"value":"inspectable","primary":true,"reason":null}],"conflict":[{"value":"llm-arbitrate","primary":true,"reason":"LLM-arbitrate (tool creation)"}]},"cells":{"type":{"value":"Tool creation for reasoning","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"desc":{"value":"Tool creation for disentangling abstract and concrete reasoning. EMNLP Findings.","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"claims":{"value":"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).","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"modalities":{"value":"text","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"created":{"value":"2023-05-23 (arxiv 2305.14318 submitted May 23 2023; EMNLP 2023 Findings)","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"paper"},"latest-release":{"value":"not applicable — not OSS","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-06"},"license":{"value":"not applicable — not OSS","citation":null,"status":"not-applicable","tier":"T3"},"gh":{"value":"not applicable — no GitHub repo","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-06"},"mindshare":{"value":"70 cites · 2.0/mo · 30* / 1 forks · 8 influential SS cites","citation":"https://api.semanticscholar.org/graph/v1/paper/arXiv:2305.14318","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"paper"},"citations":{"value":"70 cites 24/yr","citation":"https://api.semanticscholar.org/graph/v1/paper/arXiv:2305.14318","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"paper"},"funding":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-06"},"customers":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"pricing":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"compliance":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"data-handling":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"deployment":{"value":"not applicable — not a deployable product","citation":null,"status":"not-applicable","tier":"T3"},"hq":{"value":"not applicable — not a company","citation":null,"status":"not-applicable","tier":"T3"},"founders":{"value":"no data — no URL in landscape HTML; searched EMNLP CREATOR tool creation reasoning","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"volume":{"value":"no scale claim — research (EMNLP Findings)","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"perf":{"value":"59.7% MATH 94.7% TabMWP 75.5% Creation Challenge","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"repro":{"value":"Independently reproduced (light): 1 forks of https://github.com/qiancheng0/CREATOR; mostly fork-only activity","citation":"https://github.com/qiancheng0/CREATOR","status":"real-data","tier":"T1","source_class":"repo"},"code-release":{"value":"Code public + weights closed — https://github.com/qiancheng0/CREATOR · stale (last commit 2023-10) · 30* / 1 forks · no license","citation":"https://github.com/qiancheng0/CREATOR","status":"real-data","tier":"T1","source_class":"repo"},"api-surface":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"latency":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"throughput":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"backend-storage":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"multi-tenancy":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"encryption":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"sso-rbac":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"embedding-model":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"not specified - paper does not address this dimension","citation":"https://arxiv.org/abs/2305.14318","status":"depth-floor-reached","tier":"T2","source_class":"paper"},"versioning":{"value":"not specified - paper does not address this dimension","citation":"https://arxiv.org/abs/2305.14318","status":"depth-floor-reached","tier":"T2","source_class":"paper"},"tombstoning":{"value":"not specified - paper does not address this dimension","citation":"https://arxiv.org/abs/2305.14318","status":"depth-floor-reached","tier":"T2","source_class":"paper"},"schema-evolution":{"value":"schema with migration","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"namespace":{"value":"not specified - paper does not address this dimension","citation":"https://arxiv.org/abs/2305.14318","status":"depth-floor-reached","tier":"T2","source_class":"paper"},"contradiction":{"value":"LLM resolves and overwrites","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"forgetting":{"value":"not specified - paper does not address this dimension","citation":"https://arxiv.org/abs/2305.14318","status":"depth-floor-reached","tier":"T2","source_class":"paper"},"mcp-support":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"a2a-support":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"otel":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"webhooks":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"import-export":{"value":"not applicable — research paper, no deployed product","citation":null,"status":"not-applicable","tier":"T3"},"integration-count":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"orchestration":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"programmatic-control":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"vendor-benchmarks":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-06"},"pricing-specifics":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"agent-abstraction":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"memory-primitives":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"llm-lock":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"runtimes":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"session-handling":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"validated-verticals":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"time-to-running":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"anti-fit":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"optimised-for":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"adjacent-infrastructure":{"value":"not applicable - research paper","citation":null,"status":"not-applicable","tier":"T3"},"pros":{"value":"Tool creation for disentangling abstract and concrete reasoning; EMNLP Findings.","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"cons":{"value":"Created tools quality varies; tool reuse across domains is brittle.","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"links":{"value":"ACL Anthology","citation":"https://arxiv.org/abs/2305.14318","status":"real-data","tier":"T2","source_class":"paper"},"obs-langsmith":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-opentelemetry":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-datadog":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-helicone":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-weave":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-langfuse":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-arize":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-custom":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-token-budget":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-prompt-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-semantic-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-batching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-model-routing":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-streaming-only":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-observability-cost-attribution":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-langsmith-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-braintrust":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-weights-and-biases-agent":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-helicone-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-custom-test-harness":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-human-loop":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-production-traffic-replay":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"commit-trajectory":{"value":"not applicable — no GitHub repo","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"citation-trajectory":{"value":"[{\"year\":2023,\"cum\":1,\"infl\":0},{\"year\":2025,\"cum\":4,\"infl\":0}]","citation":"https://www.semanticscholar.org/paper/arXiv:2305.14318","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"paper"},"download-trajectory":{"value":"not applicable — not published as a package","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"cost-input-usd-per-mtok":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"cost-output-usd-per-mtok":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"cost-tier":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"cost-pricing-model":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"cost-last-verified":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"capability-composite-score":{"value":"not applicable — research paper on tool-creation reasoning method, not a deployed product","citation":null,"status":"not-applicable","tier":"T3"},"capability-band":{"value":"not applicable — research paper on tool-creation reasoning method, not a deployed product","citation":null,"status":"not-applicable","tier":"T3"},"capability-benchmark-sources":{"value":"not applicable — research paper on tool-creation reasoning method, not a deployed product","citation":null,"status":"not-applicable","tier":"T3"},"capability-last-verified":{"value":"not applicable — research paper on tool-creation reasoning method, not a deployed product","citation":null,"status":"not-applicable","tier":"T3"},"use-case-tags":{"value":"not applicable — research paper on tool creation for reasoning, no deployable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — research paper on tool creation for reasoning, no deployable system","citation":null,"status":"not-applicable","tier":"T3"},"adoption-accelerator":{"value":"","citation":null,"status":"no-data","tier":"T3"},"architecture-deployment-locus":{"value":"","citation":null,"status":"no-data","tier":"T3"},"licensing-bucket":{"value":"not applicable — research paper","citation":null,"status":"not-applicable","tier":"T3"},"positioning-platform-vs-product":{"value":"","citation":null,"status":"no-data","tier":"T3"},"taxonomy-three-layer-rollup":{"value":"agent-infra","citation":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/docs/schema/section-to-three-layer-rollup.json","status":"real-data","tier":"T1","source_class":"repo"},"developer-activity-opendigger":{"value":"","citation":null,"status":"no-data","tier":"T3"},"freshness-date":{"value":"2026-10-28","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/creator","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"","citation":null,"status":"no-data","tier":"T3"},"sdk-languages":{"value":"","citation":null,"status":"no-data","tier":"T3"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":19,"third_party_cells":0},"edges":{"outgoing":[],"incoming":[]},"history":[],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}