{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.29626", "kind": "paper", "url": "https://arxiv.org/abs/2607.29626"}], "authors": ["Tianyu Huai", "Tingshuo Fan", "Xinchi Chen", "Yining Zheng", "Yuxin Wang", "Shuang Chen", "Jie Zhou", "Xuanjing Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.29626", "source_url": "https://arxiv.org/abs/2607.29626"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "AgentHPOBench evaluates LLM agents as sequential hyperparameter optimizers across 30 executable ML tasks. Agents observe accumulated configurations, metrics, and logs, then propose the next configuration. Scoring compares agents and conventional HPO baselines under a unified protocol."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.29626", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.29626", "title": "AgentHPOBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Fudan University", "East China Normal University", "Shanghai Innovation Institute"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.29626", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.29626", "source_url": "https://openalex.org/W7172315228"}, "key": "claire-radar:2607.29626", "modality": null, "name": "AgentHPOBench", "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_agenthpobench_61915136", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f3f714208937cf6d03c06215388b106773029f49c816b1f4dbd7e88ce65a837d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.29626"}, "publisher": null, "released": "2026-07-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.29626", "source_url": "https://arxiv.org/abs/2607.29626"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-29626", "source": "claire_radar", "source_benchmark_id": "2607.29626", "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/2607.29626", "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": "6e96b78ef967b4aaa652baba8aedfc43c3141d44ed9ae91a41f1399a880dedae", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AgentHPOBench evaluates LLM agents as sequential hyperparameter optimizers across 30 executable ML tasks. Agents observe accumulated configurations, metrics, and logs, then propose the next configuration. Scoring compares agents and conventional HPO baselines under a unified protocol.", "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": "To address this gap, we introduce AgentHPOBench, a sequential benchmark comprising 30 executable machine learning tasks across seven research categories."}, "familyId": "bmf_c788cbfe6bdb", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_agenthpobench_61915136", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.29626", "paper": "https://arxiv.org/abs/2607.29626", "pdf": "https://arxiv.org/pdf/2607.29626", "project": null, "report": "https://arxiv.org/abs/2607.29626"}, "metrics": [], "motivation": "As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly important.", "name": "AgentHPOBench", "oneLine": "AgentHPOBench evaluates LLM agents as sequential hyperparameter optimizers across 30 executable ML tasks. Agents observe accumulated configurations, metrics, and logs, then propose the next configuration. Scoring compares agents and conventional HPO baselines under a unified protocol.", "paperTitle": "AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.29626", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "AgentHPOBench team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.29626"}], "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": "2026-07-31", "source": {"authors": ["Tianyu Huai", "Tingshuo Fan", "Xinchi Chen", "Yining Zheng", "Yuxin Wang", "Shuang Chen", "Jie Zhou", "Xuanjing Huang"], "categories": ["cs.AI"], "id": "2607.29626", "title": "AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers", "type": "arxiv", "url": "https://arxiv.org/abs/2607.29626"}, "sourceUpdatedAt": "2026-07-31T16:58:00Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing benchmarks do not directly assess whether agents can interpret experimental evidence and use it to guide subsequent hyperparameter decisions. AgentHPOBench provides a repeatable protocol for measuring iterative decision-making, filling a gap in evaluating autonomous scientific agents."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
