{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.28158", "kind": "paper", "url": "https://arxiv.org/abs/2605.28158"}, {"id": "gh:0xzhouchenyu/or-space", "kind": "repo", "url": "https://github.com/0xzhouchenyu/OR-Space"}], "authors": ["Chenyu Zhou", "Xinyun Lu", "Jiangyue Zhao", "Jianghao Lin", "Dongdong Ge", "Yinyu Ye"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.28158", "source_url": "https://arxiv.org/abs/2605.28158"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "A full-lifecycle workspace benchmark for industrial optimization agents, evaluating model construction, revision, and grounded explanation across three task modes (Build, Revise, Explain) using executable multi-file workspaces with task-specific evaluators."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.28158", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.28158", "title": "OR-Space"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Jiao Tong University", "Shanghai University of Finance and Economics", "Stanford University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.28158", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.28158", "source_url": "https://openalex.org/W7162663127"}, "key": "claire-radar:2605.28158", "modality": null, "name": "OR-Space", "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_or-space_6e200388", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d5d84f014f867fefdec4d436905e28c2a2ddd1f946c2f44e5db2ee5e8a0aa1c5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.28158"}, "publisher": null, "released": "2026-05-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.28158", "source_url": "https://arxiv.org/abs/2605.28158"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-28158", "source": "claire_radar", "source_benchmark_id": "2605.28158", "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/0xzhouchenyu/OR-Space", "githubScope": "benchmark_repo", "githubStars": 14, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 4, "hfPaperUrl": "https://huggingface.co/papers/2605.28158", "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": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "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": "2275bbeddc868adc4d82c8d69ac82a5139372958660412e16d8e3ccf0ac8f78d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A full-lifecycle workspace benchmark for industrial optimization agents, evaluating model construction, revision, and grounded explanation across three task modes (Build, Revise, Explain) using executable multi-file workspaces with task-specific evaluators.", "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"], "snippet": "We introduce OR-Space, a full-lifecycle workspace benchmark for evaluating industrial optimization agents across model construction, model revision, and grounded explanation."}, "familyId": "bmf_3a4d8160cbad", "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/0xzhouchenyu/OR-Space", "url": "https://github.com/0xzhouchenyu/OR-Space"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/0xzhouchenyu/OR-Space", "url": "https://huggingface.co/papers/2605.28158"}], "scope": "benchmark_repo", "url": "https://github.com/0xzhouchenyu/OR-Space", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_or-space_6e200388", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/0xzhouchenyu/OR-Space", "data": null, "hfPaper": "https://huggingface.co/papers/2605.28158", "paper": "https://arxiv.org/abs/2605.28158", "pdf": "https://arxiv.org/pdf/2605.28158", "project": null, "report": "https://arxiv.org/abs/2605.28158"}, "metrics": [], "motivation": "Large language model (LLM) agents are increasingly used to assist with operations research (OR) modeling, yet existing OR-oriented benchmarks often reduce evaluation to one-shot translation from a self-contained problem statement into a mathematical formulation or solver program.", "name": "OR-Space", "oneLine": "A full-lifecycle workspace benchmark for industrial optimization agents, evaluating model construction, revision, and grounded explanation across three task modes (Build, Revise, Explain) using executable multi-file workspaces with task-specific evaluators.", "paperTitle": "OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.28158", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "OR-Space team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/0xzhouchenyu/OR-Space"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-27", "source": {"authors": ["Chenyu Zhou", "Xinyun Lu", "Jiangyue Zhao", "Jianghao Lin", "Dongdong Ge", "Yinyu Ye"], "categories": ["cs.AI"], "id": "2605.28158", "title": "OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2605.28158"}, "sourceUpdatedAt": "2026-05-27T08:41:30Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Fills the gap in benchmarking LLM agents for real industrial OR workflows, where persistent multi-artifact workspaces and multi-stage lifecycles are central, offering a more realistic evaluation of practical readiness beyond single-shot formulation tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
