{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.06960", "kind": "paper", "url": "https://arxiv.org/abs/2606.06960"}], "authors": ["Yining Zhu", "Zihao Deng", "Leiming Wang", "Jingfei Lu", "Junbo Wang", "Yuke Li", "Jikun Shen", "Chuncheng Ran"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.06960", "source_url": "https://arxiv.org/abs/2606.06960"}, "categories": ["Agents", "Finance", "Language & Knowledge", "Self-Evolution"], "description": {"en": "FinEvolveBench evaluates self-evolving agents on low-repetition financial prediction tasks with implicit rewards, measuring utility updates over delayed returns."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.06960", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.06960", "title": "FinEvolveBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.06960", "modality": null, "name": "FinEvolveBench", "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_finevolvebench_f7d5f81e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3d734a3021220721603537459dff373f36d35c3230b5eb47f6907ec0d20456d1", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.06960"}, "publisher": null, "released": "2026-06-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.06960", "source_url": "https://arxiv.org/abs/2606.06960"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-06960", "source": "claire_radar", "source_benchmark_id": "2606.06960", "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/2606.06960", "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": "4ba5afdbdb140318753e941814557bf9a79b8ff11be109c9725c9bd594eed771", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FinEvolveBench evaluates self-evolving agents on low-repetition financial prediction tasks with implicit rewards, measuring utility updates over delayed returns.", "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 \\textsc{FinEvolveBench}, a benchmark for self-evolving agents on low-repetition tasks with implicit rewards."}, "familyId": "bmf_bdf52b68aa6a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_finevolvebench_f7d5f81e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.06960", "paper": "https://arxiv.org/abs/2606.06960", "pdf": "https://arxiv.org/pdf/2606.06960", "project": null, "report": "https://arxiv.org/abs/2606.06960"}, "metrics": [], "motivation": "Experience-based self-evolution enables language-model agents to improve their behavior by accumulating and updating experience at test time, yet existing evaluations often assume recurring task patterns and explicit success signals.", "name": "FinEvolveBench", "oneLine": "FinEvolveBench evaluates self-evolving agents on low-repetition financial prediction tasks with implicit rewards, measuring utility updates over delayed returns.", "paperTitle": "FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.06960", "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": "2026-06-05", "source": {"authors": ["Zihao Deng", "Yining Zhu", "Leiming Wang", "Jingfei Lu", "Junbo Wang", "Chuncheng Ran", "Yu Yang", "Dixuan Yang", "Jikun Shen"], "categories": ["cs.CL"], "id": "2606.06960", "title": "FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards", "type": "arxiv", "url": "https://arxiv.org/abs/2606.06960"}, "sourceUpdatedAt": "2026-08-12T07:10:01Z", "topics": ["Self-Evolution", "Agents"], "venueAttempts": [], "whyItMatters": "Addresses evaluation of experience-based self-evolution under noisy feedback, relevant for agent adaptation, but lacks public comparison path."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
