{"id":"smartplay--gh-microsoft-smartplay","name":"SmartPlay","url":"https://github.com/Microsoft/SmartPlay","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/smartplay--gh-microsoft-smartplay","family":"memory-research","section":"Memory benchmarks & evaluation","sections":["Memory benchmarks & evaluation"],"tier":3,"last_verified_at":"2026-10-28","lifecycle":{"status":"archived","severity":3,"note":"repository archived (read-only)"},"taxonomy":{"storage":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"retrieval":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"persistence":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"update":[{"value":"read-only","primary":true,"reason":null}],"unit":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"governance":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"conflict":[{"value":"n/a","primary":true,"reason":"not applicable — read-only evaluation dataset"}]},"cells":{"type":{"value":"LLM-agent benchmark across 6 games — Microsoft Research","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"desc":{"value":"Microsoft Research's SmartPlay — LLM-agent benchmark on 6 games (Bandits, Rock-Paper-Scissors, Tower of Hanoi, MessengerEnv, Crafter, Minecraft). Tests 9 distinct capability axes including object understanding, planning, generalisation, error-handling, theory-of-mind. ICLR 2024. Bridges narrow-task benchmarks (MMLU) and full-agent benchmarks (AgentBench).","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"claims":{"value":"ICLR 2024; 9 capability axes evaluated across 6 games; GPT-4 SOTA at time of release","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"modalities":{"value":"text-converted game state (LLM-interfacing layer)","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"created":{"value":"2023-10 (Wu et al. arXiv 2310.01557)","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"latest-release":{"value":"not applicable — not OSS","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"license":{"value":"MIT","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"gh":{"value":"170★ Python","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"mindshare":{"value":"Microsoft Research; one of the few systematic LLM-agent-vs-games benchmarks","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citations":{"value":"80+ cites — Wu et al. ICLR 2024","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"funding":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"customers":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"pricing":{"value":"not applicable — open benchmark; free to use","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"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 — run locally","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"hq":{"value":"not applicable — not a company","citation":null,"status":"not-applicable","tier":"T3"},"founders":{"value":"Yue Wu, Xuan Tang, Tom M. Mitchell, Yuanzhi Li (Microsoft Research / CMU)","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"volume":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"perf":{"value":"not applicable — does not compete on benchmarks","citation":null,"status":"not-applicable","tier":"T3"},"repro":{"value":"Independently reproduced — multiple LLM-agent papers cite results","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"code-release":{"value":"Code public","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"api-surface":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"latency":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"throughput":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"backend-storage":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"multi-tenancy":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"encryption":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"sso-rbac":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"embedding-model":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"versioning":{"value":"not applicable — static benchmark","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"tombstoning":{"value":"not applicable — static benchmark","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"schema-evolution":{"value":"not applicable — fixed evaluation dataset","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"namespace":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"contradiction":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"forgetting":{"value":"not applicable — static benchmark","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"mcp-support":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"a2a-support":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"otel":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"webhooks":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"import-export":{"value":"not applicable — benchmark / evaluation harness","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":"2026-05-14"},"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 - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"time-to-running":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"anti-fit":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"optimised-for":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"adjacent-infrastructure":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"pros":{"value":"9 capability axes give finer-grained agent capability picture than single-task benchmarks; lightweight (LLM-interface, not full RL).","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"cons":{"value":"Text-only LLM interface bypasses perception; 6-game set is narrow; ICLR 2024 already feels dated vs newer agent benchmarks.","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"links":{"value":"github.com/Microsoft/SmartPlay arxiv 2310.01557","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"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":"[{\"ym\":\"2023-10\",\"cum\":33},{\"ym\":\"2023-11\",\"cum\":48},{\"ym\":\"2023-12\",\"cum\":56},{\"ym\":\"2024-04\",\"cum\":58}]","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"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":"0","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"cost-tier":{"value":"free","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"cost-pricing-model":{"value":"free-tier","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"cost-last-verified":{"value":"2026-06-29","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"capability-composite-score":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-band":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-benchmark-sources":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-last-verified":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-tags":{"value":"not applicable — benchmark, not a deployable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — benchmark, not a 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":"open-source","citation":"https://github.com/Microsoft/SmartPlay","status":"real-data","tier":"T1","source_class":"repo"},"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":"searched not found","citation":"https://oss.open-digger.cn/github/Microsoft/SmartPlay/openrank.json","status":"depth-floor-reached","tier":"T2","source_class":"third-party"},"freshness-date":{"value":"2026-10-28","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/smartplay--gh-microsoft-smartplay","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":29,"third_party_cells":0},"edges":{"outgoing":[],"incoming":[]},"history":[{"date":"2026-10-22","commit":"89dcc719ed","pr":195,"kind":"lifecycle","changes":[{"field":"decay_cause","label":"Lifecycle","from":"","to":"archived","first":true}]}],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}