{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.06144", "kind": "paper", "url": "https://arxiv.org/abs/2608.06144"}], "authors": ["Bo Deng", "Kang Zhou", "Lifan Guo", "Chongyang Tao", "Xuanren Chen", "Chenggang Xie", "Renzhao Liang", "Feng Chen", "Chi Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.06144", "source_url": "https://arxiv.org/abs/2608.06144"}, "categories": ["Agents", "Finance", "Language & Knowledge", "Self-Evolution"], "description": {"en": "FinEvo-Bench evaluates self-evolving agents on 120 real-case-grounded tasks across 20 business scenes in six financial domains, with institution-provided procedures and rubrics for quality and compliance."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.06144", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.06144", "title": "FinEvo-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Alibaba Group (China)", "Beihang University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.06144", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.06144", "source_url": "https://openalex.org/W7201871502"}, "key": "claire-radar:2608.06144", "modality": null, "name": "FinEvo-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_finevo-bench_09755690", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "734df28d9643a2b819d70e02bdd79aa2263350d2accba72d1531edd134714f84", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.06144"}, "publisher": null, "released": "2026-08-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.06144", "source_url": "https://arxiv.org/abs/2608.06144"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-06144", "source": "claire_radar", "source_benchmark_id": "2608.06144", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.06144", "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": "a4b4a94906f9eef5f72c45bd3104639dee614322b0ec00ee21e698d1a919a589", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FinEvo-Bench evaluates self-evolving agents on 120 real-case-grounded tasks across 20 business scenes in six financial domains, with institution-provided procedures and rubrics for quality and compliance.", "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 FinEvo-Bench, a longitudinal benchmark with 120 real-case-grounded tasks, 20 business scenes across six financial domains."}, "familyId": "bmf_46e0c5291976", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_finevo-bench_09755690", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.06144", "paper": "https://arxiv.org/abs/2608.06144", "pdf": "https://arxiv.org/pdf/2608.06144", "project": null, "report": "https://arxiv.org/abs/2608.06144"}, "metrics": [], "motivation": "Most agent benchmarks evaluate tasks independently and cannot measure whether experience from one task helps with later tasks.", "name": "FinEvo-Bench", "oneLine": "FinEvo-Bench evaluates self-evolving agents on 120 real-case-grounded tasks across 20 business scenes in six financial domains, with institution-provided procedures and rubrics for quality and compliance.", "paperTitle": "FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.06144", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "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": "2026-08-06", "source": {"authors": ["Bo Deng (1 and 2)", "Kang Zhou (2)", "Lifan Guo (2)", "Chongyang Tao (1)", "Xuanren Chen (1)", "Chenggang Xie (1)", "Renzhao Liang (1)", "Feng Chen (2)", "Chi Zhang (2) ((1) Beihang University", "(2) Qwen DianJin Team", "Alibaba Cloud Computing)"], "categories": ["cs.AI"], "id": "2608.06144", "title": "FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows", "type": "arxiv", "url": "https://arxiv.org/abs/2608.06144"}, "sourceUpdatedAt": "2026-08-06T15:14:54Z", "topics": ["Self-Evolution", "Agents"], "venueAttempts": [], "whyItMatters": "Most agent benchmarks treat tasks independently and cannot measure learning from experience. FinEvo-Bench provides a longitudinal evaluation that measures both professional performance and self-evolution ability, filling a gap in agent benchmarking."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
