{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.19787", "kind": "paper", "url": "https://arxiv.org/abs/2606.19787"}], "authors": ["Jiajun Li", "Mingshu Cai", "Yixuan Li", "Yu Ding", "Ran Hou", "Guanyu Nie", "Xiongwei Han", "Wanyuan Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.19787", "source_url": "https://arxiv.org/abs/2606.19787"}, "categories": ["Agents & Tool Use", "General AI", "cs.AI"], "description": {"en": "ORAgentBench evaluates autonomous agents on end-to-end operations research tasks. Each task involves a natural-language brief, multi-file data, configuration artifacts, and a required submission schema. Agents write and run solution code, validated for schema, hard constraints, and objective quality."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.19787", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.19787", "title": "ORAgentBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Southeast University", "Waseda University", "Nanyang Technological University", "Huawei Technologies (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.19787", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.19787", "source_url": "https://openalex.org/W7165401407"}, "key": "claire-radar:2606.19787", "modality": null, "name": "ORAgentBench", "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_oragentbench_12c4a136", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0d2e7e02a25f1f79fcdfe303679a6b6f484148cadea1d6f9574c30f1703e37d6", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.19787"}, "publisher": null, "released": "2026-06-18", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.19787", "source_url": "https://arxiv.org/abs/2606.19787"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-19787", "source": "claire_radar", "source_benchmark_id": "2606.19787", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.19787", "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": "2026-10-04", "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": "0669a1b6c4df86f9221fe089a6208124c0ce3b53ab803c950ffda48a329083c4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ORAgentBench evaluates autonomous agents on end-to-end operations research tasks. Each task involves a natural-language brief, multi-file data, configuration artifacts, and a required submission schema. Agents write and run solution code, validated for schema, hard constraints, and objective quality.", "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": "In this work, we introduce ORAgentBench, an execution-grounded benchmark for evaluating autonomous agents on challenging end-to-end operations research tasks."}, "familyId": "bmf_617a34730963", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_oragentbench_12c4a136", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.19787", "paper": "https://arxiv.org/abs/2606.19787", "pdf": "https://arxiv.org/pdf/2606.19787", "project": null, "report": "https://arxiv.org/abs/2606.19787"}, "metrics": [], "motivation": "Large language models are increasingly deployed as autonomous agents for multi-step tasks in executable environments, yet their ability to perform realistic operations research (OR) work remains unclear.", "name": "ORAgentBench", "oneLine": "ORAgentBench evaluates autonomous agents on end-to-end operations research tasks. Each task involves a natural-language brief, multi-file data, configuration artifacts, and a required submission schema. Agents write and run solution code, validated for schema, hard constraints, and objective quality.", "paperTitle": "ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.19787", "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": "2026-06-18", "source": {"authors": ["Jiajun Li", "Mingshu Cai", "Yixuan Li", "Yu Ding", "Ran Hou", "Guanyu Nie", "Xiongwei Han", "Wanyuan Wang"], "categories": ["cs.AI"], "id": "2606.19787", "title": "ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?", "type": "arxiv", "url": "https://arxiv.org/abs/2606.19787"}, "sourceUpdatedAt": "2026-06-18T04:43:23Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing OR evaluations often decouple modeling from solving and rarely test full workflows from artifacts to validated decisions. ORAgentBench provides a realistic, execution-grounded protocol for measuring practical decision-making in operations research, helping to identify strategic weaknesses in current models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
