{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.18423", "kind": "paper", "url": "https://arxiv.org/abs/2608.18423"}, {"id": "gh:analogy-ai/fm-bench", "kind": "repo", "url": "https://github.com/Analogy-AI/fm-bench"}], "authors": ["Tianyou Wang", "Chongyang Gao", "Kezhen Chen", "Dong Chen", "Yinghao He", "Donghan Li", "Wangcheng Xu", "Hongjiu Zhang", "Chi Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.18423", "source_url": "https://arxiv.org/abs/2608.18423"}, "categories": ["Finance", "Language & Knowledge", "cs.AI"], "description": {"en": "FM-Bench evaluates LLM agents on long-horizon football club management through 20 in-game years with 26 tools, measuring managerial decision quality via a deterministic engine scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.18423", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.18423", "title": "FM-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.18423", "modality": null, "name": "FM-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_fm-bench_85cc4c12", "origin_source": "arxiv", "recognition_confidence": "0.75", "record_sha256": "09eac5cf7e68be47610a946a8cf146fdb4ac2e9d6c92b43ffb40058f74fbc9fd", "relation": "introduces", "review_model": "deepseek-v4-flash", "review_state": "ai-reviewed", "reviewed_at": "2026-08-20T09:45:58.504563Z", "source_url": "https://arxiv.org/abs/2608.18423"}, "publisher": null, "released": "2026-08-19", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.18423", "source_url": "https://arxiv.org/abs/2608.18423"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-18423", "source": "claire_radar", "source_benchmark_id": "2608.18423", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Analogy-AI/fm-bench", "githubScope": "benchmark_repo", "githubStars": 21, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 21, "hfPaperUrl": "https://huggingface.co/papers/2608.18423", "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": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "6e16420e979f7ab35f80e1fb00394624134919f5a8457b2c8552cb1dfa8686c2", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "Explicitly designed as a benchmark with clear scoring, code availability, and instructions for running evaluations. The abstract and code repo confirm a public reuse path and ongoing scoring via Arena.", "model": "deepseek-v4-flash", "reviewedAt": "2026-08-20T09:45:58.504563Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FM-Bench evaluates LLM agents on long-horizon football club management through 20 in-game years with 26 tools, measuring managerial decision quality via a deterministic engine scoring.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "evaluation protocol evidence", "public artifact URL"], "snippet": "FM-Bench (Football Management Benchmark) measures this."}, "familyId": "bmf_9ecdad9645f6", "firstSeenAt": "2026-08-20", "heat": null, "id": "bm_fm-bench_85cc4c12", "indexedAt": "2026-08-20T09:44:47.308583Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/Analogy-AI/fm-bench", "data": null, "paper": "https://arxiv.org/abs/2608.18423", "pdf": "https://arxiv.org/pdf/2608.18423", "project": null, "report": "https://arxiv.org/abs/2608.18423"}, "metrics": [], "motivation": "Language model agents now execute bounded tasks reliably.", "name": "FM-Bench", "oneLine": "FM-Bench evaluates LLM agents on long-horizon football club management through 20 in-game years with 26 tools, measuring managerial decision quality via a deterministic engine scoring.", "paperTitle": "FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.18423", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-20T09:44:47.308583Z"}, "publications": [], "publishers": [{"name": "Analogy AI", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Analogy-AI/fm-bench"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.4125986025698628, "value": 21}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.5461705391971857, "value": 21}}, "confidence": "Medium", "coverage": 0.7, "rank": 98, "score": 46}, "method": "attention-ranking-v13", "rank": 98, "score": 46}}, "readiness": "Runnable", "recognitionConfidence": 0.75, "relation": "introduces", "releasedAt": "2026-08-19", "source": {"authors": ["Tianyou Wang and Chongyang Gao and Kezhen Chen and Chen Dong and Yinghao He and Donghan Li and Wangcheng Xu and Hongjiu Zhang and Chi Li"], "categories": ["cs.AI"], "id": "2608.18423", "title": "FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2608.18423"}, "sourceUpdatedAt": "2026-08-19T01:33:36Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Current agent benchmarks focus on bounded tasks, leaving long-horizon decision-making unmeasured. FM-Bench provides a reproducible environment with deterministic scoring to test sustained decision quality over hundreds of steps."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
