{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.25656", "kind": "paper", "url": "https://arxiv.org/abs/2607.25656"}], "authors": ["Zhenzhen Ren", "Jiyan He", "Xinpeng Zhang", "Zhenxing Qian", "Ke Han", "Shuxin Zheng", "GuoBiao Li", "Xiaoqing Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.25656", "source_url": "https://arxiv.org/abs/2607.25656"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "OrchBench evaluates multi-agent orchestration plans in isolation using deterministic simulation. It constructs DAGs from real-world tasks and scores plans on result quality, makespan, and token cost without executing worker agents."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.25656", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.25656", "title": "OrchBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Fudan University", "Queen Mary University of London"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.25656", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.25656", "source_url": "https://openalex.org/W7171731330"}, "key": "claire-radar:2607.25656", "modality": null, "name": "OrchBench", "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_orchbench_2f9fbf5c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "2c021f932b314a848d1a72dcb89d608f325ef794655b6f2e3caa25dae850de4b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.25656"}, "publisher": null, "released": "2026-07-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.25656", "source_url": "https://arxiv.org/abs/2607.25656"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-25656", "source": "claire_radar", "source_benchmark_id": "2607.25656", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2607.25656", "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": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b87ecaf5ac12614286895adf6b43781cf1be0be29071f9ce08b2f4a9704ae3db", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "OrchBench evaluates multi-agent orchestration plans in isolation using deterministic simulation. It constructs DAGs from real-world tasks and scores plans on result quality, makespan, and token cost without executing worker agents.", "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 OrchBench, a simulation-based benchmark for evaluating multi-agent orchestration plans in isolation."}, "familyId": "bmf_11407a7c2e35", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_orchbench_2f9fbf5c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.25656", "paper": "https://arxiv.org/abs/2607.25656", "pdf": "https://arxiv.org/pdf/2607.25656", "project": null, "report": "https://arxiv.org/abs/2607.25656"}, "metrics": [], "motivation": "Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (MAS).", "name": "OrchBench", "oneLine": "OrchBench evaluates multi-agent orchestration plans in isolation using deterministic simulation. It constructs DAGs from real-world tasks and scores plans on result quality, makespan, and token cost without executing worker agents.", "paperTitle": "OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.25656", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.25656"}], "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": "2026-07-28", "source": {"authors": ["Zhenzhen Ren", "Jiyan He", "Xinpeng Zhang", "Zhenxing Qian", "Ke Han", "Shuxin Zheng", "GuoBiao Li", "Xiaoqing Zhang"], "categories": ["cs.AI"], "id": "2607.25656", "title": "OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.25656"}, "sourceUpdatedAt": "2026-07-28T12:43:34Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "OrchBench provides a fast, token-efficient evaluation of orchestration plans, decoupling planning quality from worker capabilities and environmental noise. Its simulated scores correlate strongly with real executions, enabling cost-effective comparison and diagnosis of multi-agent planners."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
