{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.27155", "kind": "paper", "url": "https://arxiv.org/abs/2607.27155"}, {"id": "gh:baidu-frontier-research/omegause-officeval", "kind": "repo", "url": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal"}, {"kind": "website", "url": "https://omegause-officeval.github.io"}], "authors": ["Jingbo Zhou", "Yusai Zhao", "Qi Bao", "Jingjia Cao", "Zhenghai Chen", "Chang Gao", "Kaiqi Guo", "Muxin Guo", "Mingxuan Li", "Xinjiang Lu", "Yanru Ma", "Yixiong Xiao", "Zenghui Zhang", "Le Zhang", "Hua Wu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.27155", "source_url": "https://arxiv.org/abs/2607.27155"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates LLM agents on long-horizon office-suite tasks from 100 practitioner-derived scenarios, scoring deliverable quality through code-based verifiers and comparing performance against economic signals of human labor time and price."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.27155", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.27155", "title": "OmegaUse-OfficeVal"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.27155", "modality": null, "name": "OmegaUse-OfficeVal", "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_omegause-officeval_6b76ef98", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "fe4770151aa5e4b226e1e242fe0d50a86bd61a9e3285ad3d9d60f319d4486b9a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.27155"}, "publisher": null, "released": "2026-07-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.27155", "source_url": "https://arxiv.org/abs/2607.27155"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-27155", "source": "claire_radar", "source_benchmark_id": "2607.27155", "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": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal", "githubScope": "benchmark_repo", "githubStars": 13, "hfDailySubmittedAt": "2026-07-30T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 12, "hfPaperUrl": "https://huggingface.co/papers/2607.27155", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "2bad570f995c8afbc6c349d2793cf84552615b7dc98214ae191a25d8c28c6e43", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLM agents on long-horizon office-suite tasks from 100 practitioner-derived scenarios, scoring deliverable quality through code-based verifiers and comparing performance against economic signals of human labor time and price.", "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", "public artifact URL"], "snippet": "We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding."}, "familyId": "bmf_7046d745096e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal", "url": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal", "url": "https://huggingface.co/papers/2607.27155"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal", "url": "https://omegause-officeval.github.io"}], "scope": "benchmark_repo", "url": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_omegause-officeval_6b76ef98", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal", "data": null, "hfPaper": "https://huggingface.co/papers/2607.27155", "paper": "https://arxiv.org/abs/2607.27155", "pdf": "https://arxiv.org/pdf/2607.27155", "project": "https://omegause-officeval.github.io", "report": "https://arxiv.org/abs/2607.27155"}, "metrics": [], "motivation": "Large language model (LLM) agents are increasingly expected to assist users in completing tasks.", "name": "OmegaUse-OfficeVal", "oneLine": "Evaluates LLM agents on long-horizon office-suite tasks from 100 practitioner-derived scenarios, scoring deliverable quality through code-based verifiers and comparing performance against economic signals of human labor time and price.", "paperTitle": "OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.27155", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Baidu Frontier Research", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/baidu-frontier-research/OmegaUse-OfficeVal"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.3522667134894853, "value": 13}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.4532127250650379, "value": 12}}, "confidence": "Medium", "coverage": 0.7, "rank": 129, "score": 41}, "method": "attention-ranking-v13", "rank": 129, "score": 41}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-29", "source": {"authors": ["Jingbo Zhou", "Yusai Zhao", "Qi Bao", "Jingjia Cao", "Zhenghai Chen", "Chang Gao", "Kaiqi Guo", "Muxin Guo", "Mingxuan Li", "Xinjiang Lu", "Yanru Ma", "Yixiong Xiao", "Zenghui Zhang", "Le Zhang", "and Hua Wu"], "categories": ["cs.AI", "cs.CL", "cs.HC"], "id": "2607.27155", "title": "OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding", "type": "arxiv", "url": "https://arxiv.org/abs/2607.27155"}, "sourceUpdatedAt": "2026-08-18T12:27:28Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing agent benchmarks rarely consider cost-effectiveness for real office workflows. This benchmark provides a way to compare agent output quality relative to human labor costs, supporting value-weighted evaluation of office automation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
