{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.23200", "kind": "paper", "url": "https://arxiv.org/abs/2608.23200"}], "authors": ["Xiao Zhang", "Qumeng Sun", "Jiahao Li", "Xiang Liu", "Bruno", "Haoyang Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.23200", "source_url": "https://arxiv.org/abs/2608.23200"}, "categories": ["Agents", "Agents & Tool Use", "Code", "Code generation", "Mathematics & Formal Science", "Reasoning", "Software & AI Compute"], "description": {"en": "Evaluates verifiable long-workflow tasks across code generation, agent-environment synthesis, mathematical reasoning, and rule following, with machine-verifiable scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.23200", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.23200", "title": "LongWoF-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.23200", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.23200", "source_url": "https://openalex.org/W7204198617"}, "key": "claire-radar:2608.23200", "modality": null, "name": "LongWoF-Bench", "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_longwof-bench_2e69a90a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4820201b5efc204aac0d74acb4e2199114204b87380e91eddfbba1270b8bcdd4", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:10:57.123445Z", "source_url": "https://arxiv.org/abs/2608.23200"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.23200", "source_url": "https://arxiv.org/abs/2608.23200"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-23200", "source": "claire_radar", "source_benchmark_id": "2608.23200", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute", "Mathematics & Formal Science"], "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": 7, "hfPaperUrl": "https://huggingface.co/papers/2608.23200", "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": "2026-09-25", "state": "stale"}}, "status": "stale"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The benchmark addresses workflow execution, a growing area, but the niche focus on experience reuse may limit broader immediate attention.", "score": 45}, "capabilities": ["Reasoning", "Code generation"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:10:57.123445Z", "inputHash": "feff9333cde6b3b219b56e80b607257b37fe4d09872241b2107b756e7838e373", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce the Long-Workflow Benchmark (LongWoF-Bench), comprising 778 machine-verifiable tasks across code generation, agent-environment synthesis, mathematical reasoning, and rule following.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is explicitly introduced with a clear task set and verification mechanism, meeting the criteria for a public reusable benchmark.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:10:57.123445Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates verifiable long-workflow tasks across code generation, agent-environment synthesis, mathematical reasoning, and rule following, with machine-verifiable scoring.", "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"], "snippet": "To evaluate this setting, we introduce the Long-Workflow Benchmark (LongWoF-Bench), comprising 778 machine-verifiable tasks across code generation, agent-environment synthesis, mathematical reasoning, and rule following."}, "familyId": "bmf_c4a7ef102c20", "firstSeenAt": "2026-08-26", "heat": null, "id": "bm_longwof-bench_2e69a90a", "indexedAt": "2026-08-26T06:08:22.244942Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.23200", "pdf": "https://arxiv.org/pdf/2608.23200", "project": null, "report": "https://arxiv.org/abs/2608.23200"}, "metrics": [], "motivation": "Large language models are increasingly expected to execute complex workflows whose success depends on maintaining interdependent constraints and producing artifacts that satisfy strict end-to-end verification.", "name": "LongWoF-Bench", "oneLine": "Evaluates verifiable long-workflow tasks across code generation, agent-environment synthesis, mathematical reasoning, and rule following, with machine-verifiable scoring.", "paperTitle": "LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.23200", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-26T06:08:22.244942Z"}, "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": 0.3674261111536563, "value": 7}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 48}, "method": "attention-ranking-v13", "rank": null, "score": 48}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Xiao Zhang", "Qumeng Sun", "Jiahao Li", "Yiming Ren", "Xiang Liu", "Haoyang Zhang", "Junjie Wang"], "categories": ["cs.CL"], "id": "2608.23200", "title": "LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks", "type": "arxiv", "url": "https://arxiv.org/abs/2608.23200"}, "sourceUpdatedAt": "2026-08-25T12:35:20Z", "topics": ["Agents", "Code", "Reasoning"], "venueAttempts": [], "whyItMatters": "Provides a reusable benchmark for studying experience reuse in long-horizon LLM workflows, offering a standardized testbed for approaches like EvoMap."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
