{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.17459", "kind": "paper", "url": "https://arxiv.org/abs/2606.17459"}], "authors": ["Yuyang Dai", "Xueqing Peng", "Lingfei Qian", "Zhuohan Xie"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.17459", "source_url": "https://arxiv.org/abs/2606.17459"}, "categories": ["Agents", "Agents & Tool Use", "General AI"], "description": {"en": "CEO-Bench evaluates LLM agents on strategic resource allocation in multi-round organizational simulations with conflicting advisor inputs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.17459", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.17459", "title": "CEO-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Yale University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.17459", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.17459", "source_url": "https://openalex.org/W7164986221"}, "key": "claire-radar:2606.17459", "modality": null, "name": "CEO-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_ceo-bench_8522cfe6", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "aa9a9c40647e96d29fa928868d2fe94cc399f3dd059c92fdbc761336cbd9d7d4", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.17459"}, "publisher": null, "released": "2026-06-16", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.17459", "source_url": "https://arxiv.org/abs/2606.17459"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-17459", "source": "claire_radar", "source_benchmark_id": "2606.17459", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2606.17459", "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": "ea7bd26324aaef54d6f5707b8237bae89164ce5c426f4d18250dae4f1ea69759", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CEO-Bench evaluates LLM agents on strategic resource allocation in multi-round organizational simulations with conflicting advisor inputs.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce \\textsc{CEO-Bench}, a multi-agent benchmark that evaluates LLMs on CEO-level strategic resource reallocation -- the process of redirecting capital across business units in a multi-round, constraint-rich organizational environment."}, "familyId": "bmf_a0f9a9f93e4d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_ceo-bench_8522cfe6", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.17459", "paper": "https://arxiv.org/abs/2606.17459", "pdf": "https://arxiv.org/pdf/2606.17459", "project": null, "report": "https://arxiv.org/abs/2606.17459"}, "metrics": [], "motivation": "Evaluating the decision-making capabilities of large language models (LLMs) is a growing research priority, yet existing benchmarks focus on isolated cognitive tasks such as reasoning, knowledge retrieval, and economic rationality in stylized settings.", "name": "CEO-Bench", "oneLine": "CEO-Bench evaluates LLM agents on strategic resource allocation in multi-round organizational simulations with conflicting advisor inputs.", "paperTitle": "Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.17459", "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": "2026-06-16", "source": {"authors": ["Yuyang Dai", "Xueqing Peng", "Lingfei Qian", "Zhuohan Xie"], "categories": ["cs.AI"], "id": "2606.17459", "title": "Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation", "type": "arxiv", "url": "https://arxiv.org/abs/2606.17459"}, "sourceUpdatedAt": "2026-06-16T03:20:04Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "It probes executive decision-making capabilities beyond isolated cognitive tasks, revealing tradeoffs in agent behavior."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
