{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.27826", "kind": "paper", "url": "https://arxiv.org/abs/2606.27826"}], "authors": ["Shiyun Zhao", "Xinwei Song", "Tianyu Guo", "Xiaomeng Gao", "Mingyuan Liu", "Xu Han", "Yuanyuan Zhang", "Zhenliang Zhang", "Xue Feng", "Bo Dai"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.27826", "source_url": "https://arxiv.org/abs/2606.27826"}, "categories": ["Robotics & Embodied AI", "cs.AI"], "description": {"en": "NormAct evaluates embodied agents on 550 TongSim scenarios where the same goal permits norm-compliant or norm-violating action sequences, testing whether agents infer and apply scene-relevant social norms during ordinary tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.27826", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.27826", "title": "NormAct"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Beijing Academy of Artificial Intelligence", "ShanghaiTech University", "China Academy of Information and Communications Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.27826", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.27826", "source_url": "https://openalex.org/W7166530608"}, "key": "claire-radar:2606.27826", "modality": null, "name": "NormAct", "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_normact_ade65389", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e397cebbe53c93036e0d9105f7bd01df2f417a9e21d0bc4662a9eb168a6a1fe3", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.27826"}, "publisher": null, "released": "2026-06-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.27826", "source_url": "https://arxiv.org/abs/2606.27826"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-27826", "source": "claire_radar", "source_benchmark_id": "2606.27826", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.27826", "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", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "8e179a3fb04d0764d24772bf6ddb92b34e4c78779e77270cb417dba995d152ab", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "NormAct evaluates embodied agents on 550 TongSim scenarios where the same goal permits norm-compliant or norm-violating action sequences, testing whether agents infer and apply scene-relevant social norms during ordinary tasks.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce NormAct, a benchmark of 550 TongSim scenarios in which the same goal permits norm-compliant or norm-violating action sequences."}, "familyId": "bmf_a47d8a75095d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_normact_ade65389", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.27826", "paper": "https://arxiv.org/abs/2606.27826", "pdf": "https://arxiv.org/pdf/2606.27826", "project": null, "report": "https://arxiv.org/abs/2606.27826"}, "metrics": [], "motivation": "Embodied agents driven by multimodal large language models (MLLMs) can often complete everyday tasks from visual observations, but goal achievement does not establish whether they proactively respect unstated social norms.", "name": "NormAct", "oneLine": "NormAct evaluates embodied agents on 550 TongSim scenarios where the same goal permits norm-compliant or norm-violating action sequences, testing whether agents infer and apply scene-relevant social norms during ordinary tasks.", "paperTitle": "NormAct: Benchmarking Embodied Agents' Proactive Compliance with Unspoken Social Norms", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.27826", "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": "2026-06-26", "source": {"authors": ["Shiyun Zhao", "Xinwei Song", "Tianyu Guo", "Xiaomeng Gao", "Mingyuan Liu", "Xu Han", "Yuanyuan Zhang", "Zhenliang Zhang", "Xue Feng", "Bo Dai"], "categories": ["cs.AI"], "id": "2606.27826", "title": "NormAct: Benchmarking Embodied Agents' Proactive Compliance with Unspoken Social Norms", "type": "arxiv", "url": "https://arxiv.org/abs/2606.27826"}, "sourceUpdatedAt": "2026-08-10T02:19:01Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "NormAct addresses the gap between goal achievement and proactive norm compliance, providing a way to assess whether embodied agents respect unstated social norms without prompting, which is critical for real-world deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
