{"id":"agentic-plan-caching-apc--neurips-cc","name":"Agentic Plan Caching (APC)","url":"https://neurips.cc/virtual/2025/poster/116166","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/agentic-plan-caching-apc--neurips-cc","family":"memory-research","section":"Recent method papers — theorized, no distinct product","sections":["Recent method papers — theorized, no distinct product"],"tier":3,"last_verified_at":"2026-10-23","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":{"storage":[{"value":"kv","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 (plan-template reuse)"}]},"cells":{"type":{"value":"Test-time plan-template memory","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"desc":{"value":"Extracts, stores, adapts, and reuses structured plan templates from planning stages of agent applications. NeurIPS 2025 poster.","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"claims":{"value":"Plan template extraction from completed agent runs with keyword retrieval and lightweight model adaptation. Headline: 50.31% serving-cost reduction and 27.28% latency reduction on average while preserving 96.61% of optimal performance; baselines: Accuracy-Optimal (large planner LM, no caching) and Semantic Caching; primary datasets: FinanceBench, TabMWP, QASPER, AIME 2024/2025, GAIA.","citation":"https://arxiv.org/abs/2506.14852","status":"real-data","tier":"T2","source_class":"paper"},"modalities":{"value":"text","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"created":{"value":"2025-06","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"vendor"},"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":"11 cites · 1.0/mo","citation":"https://api.semanticscholar.org/graph/v1/paper/arXiv:2506.14852","status":"real-data","tier":"T2","last_verified_at":"2026-05-12","source_class":"paper"},"citations":{"value":"searched not found","citation":"https://arxiv.org/abs/2506.14852 (searched — count not confirmed)","status":"depth-floor-reached","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":"Qizheng Zhang, Michael Wornow, Gerry Wan, Kunle Olukotun (NeurIPS 2025 poster; arXiv 2506.14852)","citation":"https://arxiv.org/abs/2506.14852","status":"real-data","tier":"T2","source_class":"paper"},"volume":{"value":"no scale claim — research (NeurIPS 2025)","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"perf":{"value":"50.31% serving-cost reduction 96.61% of optimal performance","citation":"https://arxiv.org/abs/2506.14852","status":"real-data","tier":"T2","source_class":"paper"},"repro":{"value":"No reproductions found — published 2025-06-17 (11 mo ago); no public code","citation":"https://arxiv.org/abs/2506.14852","status":"real-data","tier":"T2","source_class":"paper"},"code-release":{"value":"depth-floor-reached: arXiv 2506.14852 preprint; no official code repo discovered via WebSearch + arXiv abstract scan + GitHub API","citation":"https://arxiv.org/abs/2506.14852","status":"real-data","tier":"T2","source_class":"paper"},"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://neurips.cc/virtual/2025/poster/116166","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"versioning":{"value":"not specified - paper does not address this dimension","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"tombstoning":{"value":"not specified - paper does not address this dimension","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"schema-evolution":{"value":"free-form / no schema","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"namespace":{"value":"not specified - paper does not address this dimension","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"contradiction":{"value":"LLM resolves and overwrites","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"forgetting":{"value":"not specified - paper does not address this dimension","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"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":"Cache-aware planning reduces repeated work for similar tasks.","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"cons":{"value":"Niche use case; cache-invalidation issues common in evolving domains.","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"links":{"value":"NeurIPS 2025 poster","citation":"https://neurips.cc/virtual/2025/poster/116166","status":"real-data","tier":"T2","source_class":"vendor"},"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":"[]","citation":"https://www.semanticscholar.org/paper/arXiv:2506.14852","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 plan-template caching, not a standalone capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-band":{"value":"not applicable — research paper on plan-template caching, not a standalone capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-benchmark-sources":{"value":"not applicable — research paper on plan-template caching, not a standalone capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-last-verified":{"value":"not applicable — research paper on plan-template caching, not a standalone capable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-tags":{"value":"not applicable — research paper on test-time plan caching, no deployable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — research paper on test-time plan caching, 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":"https://neurips.cc/virtual/2025/poster/116166","status":"not-applicable","tier":"T2","source_class":"vendor"},"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":"2026-10-23","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/agentic-plan-caching-apc--neurips-cc","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":18,"third_party_cells":0},"edges":{"outgoing":[{"source":"agentic-plan-caching-apc--neurips-cc","target":"gaia--huggingface-co","type":"cites","evidence":"S2 isInfluential citation","citation":"https://api.semanticscholar.org/graph/v1/paper/arXiv:2506.14852","isInfluential":true}],"incoming":[]},"history":[],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}