{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01912", "kind": "paper", "url": "https://arxiv.org/abs/2606.01912"}], "authors": ["Kuan Li", "Shuo Zhang", "Huacan Wang", "Fangzhou Yu", "Zecheng Sheng", "Yi Gu", "Weipeng Ming", "Lei Xue", "Chen Liu", "Sen Hu", "Ronghao Chen", "Siyue Lin", "Yuqing Hou", "Xiaofeng Mou", "Yi Xu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01912", "source_url": "https://arxiv.org/abs/2606.01912"}, "categories": ["Agents & Tool Use", "General AI", "Reasoning"], "description": {"en": "Benchmark for LLM agents in smart-home environments, with 1,100 tasks across 7 categories and 22 subcategories, built on the executable HomeEnv simulator, stratified by home complexity."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01912", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01912", "title": "SMH-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.01912", "modality": null, "name": "SMH-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_smh-bench_ef4613ad", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "19b2a4164515d750db6545f8a9769e1486a6394348531b5116ab076f1d674563", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01912"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01912", "source_url": "https://arxiv.org/abs/2606.01912"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01912", "source": "claire_radar", "source_benchmark_id": "2606.01912", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.01912", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "29c5a612b2da0a8f544596988e46f44d3b446c5c05c52d96f065c4d053529a2c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Benchmark for LLM agents in smart-home environments, with 1,100 tasks across 7 categories and 22 subcategories, built on the executable HomeEnv simulator, stratified by home complexity.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address these limitations, we introduce SMH-Bench, a comprehensive benchmark for evaluating LLMs in smart-home environments."}, "familyId": "bmf_eb0612cdd00c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_smh-bench_ef4613ad", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.01912", "paper": "https://arxiv.org/abs/2606.01912", "pdf": "https://arxiv.org/pdf/2606.01912", "project": null, "report": "https://arxiv.org/abs/2606.01912"}, "metrics": [], "motivation": "Smart homes are evolving toward complex state-dependent living environments, requiring Large Language Models (LLMs) to reason over user intent, preferences, and multi-device interactions.", "name": "SMH-Bench", "oneLine": "Benchmark for LLM agents in smart-home environments, with 1,100 tasks across 7 categories and 22 subcategories, built on the executable HomeEnv simulator, stratified by home complexity.", "paperTitle": "SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01912", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Kuan Li", "Shuo Zhang", "Huacan Wang", "Fangzhou Yu", "Zecheng Sheng", "Yi Gu", "Weipeng Ming", "Lei Xue", "Chen Liu", "Sen Hu", "Ronghao Chen", "Siyue Lin", "Yuqing Hou", "Xiaofeng Mou", "Yi Xu"], "categories": ["cs.AI"], "id": "2606.01912", "title": "SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01912"}, "sourceUpdatedAt": "2026-06-01T08:48:15Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Addresses deficiencies in existing smart-home benchmarks by evaluating state-dependent reasoning across devices, but lacks a public comparison path."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
