{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.27761", "kind": "paper", "url": "https://arxiv.org/abs/2605.27761"}], "authors": ["Yifan Sui", "Xin Huang", "Hongbing Li", "Fang Xu", "Jiahe Lv", "Haolong Yan", "Yeqing Shen", "Litao Liu", "Zhimin Fan", "Ziyang Meng", "Jia Wang", "Junbo Qi", "Kaijun Tan", "Zheng Ge", "Xiangyu Zhang", "Daxin Jiang", "Osamu Yoshie"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.27761", "source_url": "https://arxiv.org/abs/2605.27761"}, "categories": ["Agents & Tool Use", "Mobile & Personal Computing", "cs.CV"], "description": {"en": "AndroidDaily evaluates mobile GUI agents on 350 daily-use tasks across 94 closed-source Android applications. Automatic scoring is based on a three-tiered guideline system (operational obligations, output quality, negative constraints), with step-level diagnostic judgments."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.27761", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.27761", "title": "AndroidDaily"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Beijing University of Posts and Telecommunications", "StepFun AI (China)", "Waseda University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.27761", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.27761", "source_url": "https://openalex.org/W7162661743"}, "key": "claire-radar:2605.27761", "modality": null, "name": "AndroidDaily", "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_androiddaily_b00e0630", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d419f7e340d80f66a0525a6adaa52bafe8c11ceb3b483833469f846d9fd07627", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.27761"}, "publisher": null, "released": "2026-05-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.27761", "source_url": "https://arxiv.org/abs/2605.27761"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-27761", "source": "claire_radar", "source_benchmark_id": "2605.27761", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Mobile & Personal Computing"], "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/2605.27761", "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": [], "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": "0be90bbd75ad5ed9a6df958dc1c7d99f236a605154e9c36040d3f85e8de4c2cd", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AndroidDaily evaluates mobile GUI agents on 350 daily-use tasks across 94 closed-source Android applications. Automatic scoring is based on a three-tiered guideline system (operational obligations, output quality, negative constraints), with step-level diagnostic judgments.", "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": "To bridge this gap, we introduce AndroidDaily, a large-scale benchmark comprising 350 realistic daily-use tasks across 94 high-frequency Android applications spanning transportation, shopping, local services, entertainment, content creation, social media, and everyday utilities."}, "familyId": "bmf_baa4983aecb6", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_androiddaily_b00e0630", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Consumer Technology"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.27761", "paper": "https://arxiv.org/abs/2605.27761", "pdf": "https://arxiv.org/pdf/2605.27761", "project": null, "report": "https://arxiv.org/abs/2605.27761"}, "metrics": [], "motivation": "The rapid development of GUI foundation models and mobile GUI agents has spurred numerous evaluation benchmarks, yet most rely on simulated environments or open-source applications, leaving real-world closed-source applications largely unevaluated.", "name": "AndroidDaily", "oneLine": "AndroidDaily evaluates mobile GUI agents on 350 daily-use tasks across 94 closed-source Android applications. Automatic scoring is based on a three-tiered guideline system (operational obligations, output quality, negative constraints), with step-level diagnostic judgments.", "paperTitle": "AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications", "primaryDomain": "Mobile & Personal Computing", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.27761", "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": "2026-05-26", "source": {"authors": ["Yifan Sui", "Xin Huang", "Hongbing Li", "Fang Xu", "Jiahe Lv", "Haolong Yan", "Yeqing Shen", "Litao Liu", "Zhimin Fan", "Ziyang Meng", "Jia Wang", "Junbo Qi", "Kaijun Tan", "Zheng Ge", "Xiangyu Zhang", "Daxin Jiang", "Osamu Yoshie"], "categories": ["cs.CV", "cs.SE"], "id": "2605.27761", "title": "AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications", "type": "arxiv", "url": "https://arxiv.org/abs/2605.27761"}, "sourceUpdatedAt": "2026-05-26T23:19:42Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Fills evaluation gap for real-world closed-source apps where internal states are unavailable, providing a verifiable scoring method based on observable guidelines. Useful for assessing practical deployment of GUI agents."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
