{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.26546", "kind": "paper", "url": "https://arxiv.org/abs/2608.26546"}, {"kind": "website", "url": "https://dumatebench.com/"}], "authors": ["Zechun Niu", "Yukun Zhao", "Jiaxin Zhang", "Xu Shen", "Jinhua Si", "Han Tian", "Can Xu", "Yunfan Song", "Jiaxin Mao", "Yansong Gao", "Yuchen Li", "Jianmin Wu", "Lingyong Yan", "Shuaiqiang Wang", "Dawei Yin"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.26546", "source_url": "https://arxiv.org/abs/2608.26546"}, "categories": ["Agents", "Agents & Tool Use", "General AI"], "description": {"en": "Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.26546", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.26546", "title": "DuMateBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Renmin University of China", "Shandong University", "Michigan State University", "Nankai University", "Shanghai Normal University", "Baidu (China)", "Imperial College London"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.26546", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.26546", "source_url": "https://openalex.org/W7204555843"}, "key": "claire-radar:2608.26546", "modality": null, "name": "DuMateBench", "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": "true", "origin_record_id": "bm_dumatebench_7a085138", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a347a9f4ee80388cd8c33e4f034c7bfacaeb86d41d22e5644a6faab2c59b269c", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.26546"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.26546", "source_url": "https://arxiv.org/abs/2608.26546"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-26546", "source": "claire_radar", "source_benchmark_id": "2608.26546", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.26546", "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": "2026-09-27", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce DuMateBench, a real-session benchmark reconstructed from anonymized and privacy-screened user sessions collected from a large-scale production agent platform."}, "familyId": "bmf_546d4c680ff6", "firstSeenAt": "2026-08-30", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_dumatebench_7a085138", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.26546", "paper": "https://arxiv.org/abs/2608.26546", "pdf": "https://arxiv.org/pdf/2608.26546", "project": "https://dumatebench.com/", "report": "https://arxiv.org/abs/2608.26546"}, "metrics": [], "motivation": "Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings.", "name": "DuMateBench", "oneLine": "Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world settings.", "paperTitle": "DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.26546", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-27", "source": {"authors": ["Zechun Niu", "Yukun Zhao", "Jiaxin Zhang", "Xu Shen", "Jinhua Si", "Han Tian", "Can Xu", "Yunfan Song", "Jiaxin Mao", "Yansong Gao", "Yuchen Li", "Jianmin Wu", "Lingyong Yan", "Shuaiqiang Wang", "Dawei Yin"], "categories": ["cs.AI", "cs.CL"], "id": "2608.26546", "title": "DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows", "type": "arxiv", "url": "https://arxiv.org/abs/2608.26546"}, "sourceUpdatedAt": "2026-08-27T02:36:23Z", "topics": ["Agents"], "venueAttempts": []}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
