{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.10768", "kind": "paper", "url": "https://arxiv.org/abs/2607.10768"}], "authors": ["Yongchang Fu", "Xinjie Huang", "Chengjun Dai", "Chengzhe Feng", "Junshao Zhang", "Hong Zhu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.10768", "source_url": "https://arxiv.org/abs/2607.10768"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "Opti-Agent-Bench evaluates LLM agents on the end-to-end optimization R&D pipeline, from business-language description to mathematical modeling, algorithm selection, code implementation, and report generation, with modular evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.10768", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.10768", "title": "Opti-Agent-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Alibaba Group (China)", "Zhejiang University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.10768", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.10768", "source_url": "https://openalex.org/W7168252982"}, "key": "claire-radar:2607.10768", "modality": null, "name": "Opti-Agent-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_opti-agent-bench_f017ef81", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "9cb6ffac8f14462672c47c1d1b21ddcce8fc77c6c05ad85faf8441568f4cf5bb", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.10768"}, "publisher": null, "released": "2026-07-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.10768", "source_url": "https://arxiv.org/abs/2607.10768"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-10768", "source": "claire_radar", "source_benchmark_id": "2607.10768", "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/2607.10768", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "ac89ccae89caa72d72bef818a582d6b749680d08e1bbb7869dc78f93157d3bc9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Opti-Agent-Bench evaluates LLM agents on the end-to-end optimization R&D pipeline, from business-language description to mathematical modeling, algorithm selection, code implementation, and report generation, with modular evaluation.", "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 introduce Opti-Agent-Bench, an end-to-end benchmark that evaluates Large Language Models (LLMs) across the complete optimization R&D pipeline, from understanding business-language descriptions through mathematical modeling, algorithm selection, and code implementation, to solution report generation."}, "familyId": "bmf_4e5dce3ea76c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_opti-agent-bench_f017ef81", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.10768", "paper": "https://arxiv.org/abs/2607.10768", "pdf": "https://arxiv.org/pdf/2607.10768", "project": null, "report": "https://arxiv.org/abs/2607.10768"}, "metrics": [], "motivation": "LLM-based agents are increasingly deployed to solve optimization problems, yet existing benchmarks evaluate them on pre-structured mathematical formulations that bypass the most critical challenge: translating complex business requirements into correct models and solve efficiently.", "name": "Opti-Agent-Bench", "oneLine": "Opti-Agent-Bench evaluates LLM agents on the end-to-end optimization R&D pipeline, from business-language description to mathematical modeling, algorithm selection, code implementation, and report generation, with modular evaluation.", "paperTitle": "Opti-Agent-Bench: Benchmarking End-to-End Optimization R&D Agents on Real-World Business Problems", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.10768", "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/2607.10768"}], "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": "2026-07-12", "source": {"authors": ["Yongchang Fu", "Xinjie Huang", "Chengjun Dai", "Chengzhe Feng", "Junshao Zhang", "Hong Zhu"], "categories": ["cs.AI"], "id": "2607.10768", "title": "Opti-Agent-Bench: Benchmarking End-to-End Optimization R&D Agents on Real-World Business Problems", "type": "arxiv", "url": "https://arxiv.org/abs/2607.10768"}, "sourceUpdatedAt": "2026-07-12T13:47:57Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Optimization benchmarks typically test pre-structured formulations. Opti-Agent-Bench assesses the full pipeline, exposing failure modes like constraint omission and model-code inconsistency invisible under single-metric evaluation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
