{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.18191", "kind": "paper", "url": "https://arxiv.org/abs/2606.18191"}], "authors": ["Md Tawkat Islam Khondaker", "Raymond Li", "Muhammad Abdul-Mageed", "Laks V. S. Lakshmanan", "Issam H. Laradji"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.18191", "source_url": "https://arxiv.org/abs/2606.18191"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "DRFLOW evaluates an agent's ability to predict personalized workflows, sequences of action-steps, from heterogeneous sources across five domains. It includes 100 tasks with reference workflow steps and multiple diagnostic metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.18191", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.18191", "title": "DRFLOW"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.18191", "modality": null, "name": "DRFLOW", "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_drflow_2f7bee63", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e4a3526532efd41a516b3b351401c8437e613c0b00f5e9a1c20f5960de4b1a38", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.18191"}, "publisher": null, "released": "2026-06-16", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.18191", "source_url": "https://arxiv.org/abs/2606.18191"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-18191", "source": "claire_radar", "source_benchmark_id": "2606.18191", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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/2606.18191", "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": "2026-10-02", "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": "508b75b001ccec7896909217fa938ce1b4edaef5dec2911a20804095a69eed10", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "DRFLOW evaluates an agent's ability to predict personalized workflows, sequences of action-steps, from heterogeneous sources across five domains. It includes 100 tasks with reference workflow steps and multiple diagnostic metrics.", "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": "Therefore, we introduce DRFLOW, a benchmark for evaluating personalized workflows predicted by agents from heterogeneous sources."}, "familyId": "bmf_c4ede3eb8785", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_drflow_2f7bee63", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.18191", "paper": "https://arxiv.org/abs/2606.18191", "pdf": "https://arxiv.org/pdf/2606.18191", "project": null, "report": "https://arxiv.org/abs/2606.18191"}, "metrics": [], "motivation": "Deep research (DR) systems are increasingly used for complex information-seeking tasks, but existing works mainly focus on generating reports and summaries.", "name": "DRFLOW", "oneLine": "DRFLOW evaluates an agent's ability to predict personalized workflows, sequences of action-steps, from heterogeneous sources across five domains. It includes 100 tasks with reference workflow steps and multiple diagnostic metrics.", "paperTitle": "DRFLOW: A Deep Research Benchmark for Personalized Workflow Prediction", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.18191", "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": "2026-06-16", "source": {"authors": ["Md Tawkat Islam Khondaker", "Raymond Li", "Muhammad Abdul-Mageed", "Laks V. S. Lakshmanan", "Issam H. Laradji"], "categories": ["cs.AI", "cs.MA"], "id": "2606.18191", "title": "DRFLOW: A Deep Research Benchmark for Personalized Workflow Prediction", "type": "arxiv", "url": "https://arxiv.org/abs/2606.18191"}, "sourceUpdatedAt": "2026-06-17T21:10:12Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Deep research systems are typically evaluated on report generation, but enterprise tasks often require actionable workflows. DRFLOW addresses this gap by assessing workflow prediction, offering metrics for factual grounding, step recovery, and personalization, which can guide development of more practical agents."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
