{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05080", "kind": "paper", "url": "https://arxiv.org/abs/2606.05080"}, {"id": "gh:autolabhq/autolab", "kind": "repo", "url": "https://github.com/autolabhq/autolab"}, {"kind": "website", "url": "https://autolab.moe/"}], "authors": ["Zhangchen Xu", "Junda Chen", "Yue Huang", "Dongfu Jiang", "Jiefeng Chen", "Hang Hua", "Zijian Wu", "Zheyuan Liu", "Zexue He", "Lichi Li", "Shizhe Diao", "Jiaxin Pei", "Jinsung Yoon", "Hao Zhang", "Mengdi Wang", "Radha Poovendran", "Misha Sra", "Alex Pentland", "Zichen Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05080", "source_url": "https://arxiv.org/abs/2606.05080"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "AutoLab evaluates frontier models on long-horizon closed-loop optimization tasks across system optimization, CUDA kernel optimization, model development, and puzzle challenges, with 36 expert-curated tasks and a strict wall-clock budget."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05080", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05080", "title": "AutoLab"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Washington", "University of California San Diego", "University of Notre Dame", "University of Waterloo", "National University of Singapore", "Stanford University", "Princeton University", "University of California, Santa Barbara"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.05080", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.05080", "source_url": "https://openalex.org/W7163590744"}, "key": "claire-radar:2606.05080", "modality": null, "name": "AutoLab", "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_autolab_db01499e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "8ef5b7a21a010acf2c0a8fbf5b79aed82a205dc0e05308ac19292f2c13c680dd", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05080"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05080", "source_url": "https://arxiv.org/abs/2606.05080"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05080", "source": "claire_radar", "source_benchmark_id": "2606.05080", "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": "https://github.com/autolabhq/autolab", "githubScope": "benchmark_repo", "githubStars": 169, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 31, "hfPaperUrl": "https://huggingface.co/papers/2606.05080", "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": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "29758b55619444afc386cde48a9130b280acb0afc841bff305d51e0ece3b7059", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AutoLab evaluates frontier models on long-horizon closed-loop optimization tasks across system optimization, CUDA kernel optimization, model development, and puzzle challenges, with 36 expert-curated tasks and a strict wall-clock budget.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce AutoLab, a new benchmark for ultra long-horizon closed-loop optimization."}, "familyId": "bmf_5d290b897878", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/autolabhq/autolab", "url": "https://github.com/autolabhq/autolab"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/autolabhq/autolab", "url": "https://huggingface.co/papers/2606.05080"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/autolabhq/autolab", "url": "https://huggingface.co/api/papers/2606.05080"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/autolabhq/autolab/pulls", "url": "https://autolab.moe/"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/autolabhq/autolab", "url": "https://autolab.moe/"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/autolabhq/autolab", "url": "https://arxiv.org/abs/2606.05080"}], "scope": "benchmark_repo", "url": "https://github.com/autolabhq/autolab", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_autolab_db01499e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/autolabhq/autolab", "data": null, "hfPaper": "https://huggingface.co/papers/2606.05080", "paper": "https://arxiv.org/abs/2606.05080", "pdf": "https://arxiv.org/pdf/2606.05080", "project": "https://autolab.moe/", "report": "https://arxiv.org/abs/2606.05080"}, "metrics": [], "motivation": "Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts.", "name": "AutoLab", "oneLine": "AutoLab evaluates frontier models on long-horizon closed-loop optimization tasks across system optimization, CUDA kernel optimization, model development, and puzzle challenges, with 36 expert-curated tasks and a strict wall-clock budget.", "paperTitle": "AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05080", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Zhangchen Xu", "Junda Chen", "Yue Huang", "Dongfu Jiang", "Jiefeng Chen", "Hang Hua", "Zijian Wu", "Zheyuan Liu", "Zexue He", "Lichi Li", "Shizhe Diao", "Jiaxin Pei", "Jinsung Yoon", "Hao Zhang", "Mengdi Wang", "Radha Poovendran", "Misha Sra", "Alex Pentland", "Zichen Chen"], "categories": ["cs.AI", "cs.LG"], "id": "2606.05080", "title": "AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05080"}, "sourceUpdatedAt": "2026-06-03T16:36:54Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Fills the gap in evaluating sustained iterative improvement in agents, moving beyond single-turn or short-horizon benchmarks to test persistence and empirical feedback incorporation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
