{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.00107", "kind": "paper", "url": "https://arxiv.org/abs/2608.00107"}], "authors": ["Natan Vidra", "Alina Kapanova", "Arun Kanhai", "Spurthi Setty"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.00107", "source_url": "https://arxiv.org/abs/2608.00107"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "MetaRoute-Bench is an open framework for comparing meta-decision policies in agentic workflow routing. Contains 180 synthetic task profiles, eight routing policies, and 30 seeds, evaluating success, cost, and latency through 43,200 traces. Metrics include success rate and paired confidence intervals."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.00107", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.00107", "title": "MetaRoute-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Cornell University", "Stevens Institute of Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.00107", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.00107", "source_url": "https://openalex.org/W7172420153"}, "key": "claire-radar:2608.00107", "modality": null, "name": "MetaRoute-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": "unknown", "origin_record_id": "bm_metaroute-bench_a64b1073", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0f84fb23e4935c8134ab171cf48cfe055bff59ba6e8de953bb5d1af5cfc56f6f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.00107"}, "publisher": null, "released": "2026-07-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.00107", "source_url": "https://arxiv.org/abs/2608.00107"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-00107", "source": "claire_radar", "source_benchmark_id": "2608.00107", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2608.00107", "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": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b26f1040e6a5316c1e7822e89434fcac4045ac80b2665ade155a93efcd9bedd2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MetaRoute-Bench is an open framework for comparing meta-decision policies in agentic workflow routing. Contains 180 synthetic task profiles, eight routing policies, and 30 seeds, evaluating success, cost, and latency through 43,200 traces. Metrics include success rate and paired confidence intervals.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present MetaRoute-Bench, an open, inspectable framework for comparing meta-decision policies under a shared execution model."}, "familyId": "bmf_fd31642f325d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_metaroute-bench_a64b1073", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.00107", "paper": "https://arxiv.org/abs/2608.00107", "pdf": "https://arxiv.org/pdf/2608.00107", "project": null, "report": "https://arxiv.org/abs/2608.00107"}, "metrics": [], "motivation": "Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an intermediate result, or recover from failure.", "name": "MetaRoute-Bench", "oneLine": "MetaRoute-Bench is an open framework for comparing meta-decision policies in agentic workflow routing. Contains 180 synthetic task profiles, eight routing policies, and 30 seeds, evaluating success, cost, and latency through 43,200 traces. Metrics include success rate and paired confidence intervals.", "paperTitle": "MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.00107", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.00107"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-31", "source": {"authors": ["Natan Vidra", "Alina Kapanova", "Arun Kanhai", "and Spurthi Setty"], "categories": ["cs.LG", "cs.AI"], "id": "2608.00107", "title": "MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing", "type": "arxiv", "url": "https://arxiv.org/abs/2608.00107"}, "sourceUpdatedAt": "2026-07-31T07:01:21Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Meta-decisions in agentic systems are often embedded and evaluated only via aggregate task accuracy. MetaRoute-Bench provides a shared execution model to compare routing policies, enabling analysis of tradeoffs between success, cost, and latency."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
