{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03318", "kind": "paper", "url": "https://arxiv.org/abs/2606.03318"}, {"id": "gh:miaow-lab/rut-bench", "kind": "repo", "url": "https://github.com/Miaow-Lab/RUT-Bench"}], "authors": ["Xuan Yang", "Hao Xu", "Tingfeng Hui", "Hongsheng Xin", "Kaike Zhang", "Chunxiao Liu", "Ning Miao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03318", "source_url": "https://arxiv.org/abs/2606.03318"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "RUT-Bench evaluates LLM tool-use in realistic user interactions with 1,638 test samples across 59 executable environments, measuring success rate, informational honesty, and tool discipline."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03318", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03318", "title": "RUT-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["City University of Hong Kong", "Beijing University of Posts and Telecommunications"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.03318", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.03318", "source_url": "https://openalex.org/W7163391320"}, "key": "claire-radar:2606.03318", "modality": null, "name": "RUT-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_rut-bench_450993d2", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "a3f9616a23972d1b8586093a5fd052c8c6478246a9fc3dc37661a30f5d796b3c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03318"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03318", "source_url": "https://arxiv.org/abs/2606.03318"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03318", "source": "claire_radar", "source_benchmark_id": "2606.03318", "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/Miaow-Lab/RUT-Bench", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.03318", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "766ccf7f34b8bcb3e7e183803401b6f74fd5906f8bc422861e2e30d391e44643", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RUT-Bench evaluates LLM tool-use in realistic user interactions with 1,638 test samples across 59 executable environments, measuring success rate, informational honesty, and tool discipline.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To fill this gap, we propose RUT-Bench, a dedicated benchmark designed to assess LLMs under diverse Real-world User Tool calling scenarios."}, "familyId": "bmf_85a551e57aea", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Miaow-Lab/RUT-Bench", "url": "https://github.com/Miaow-Lab/RUT-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Miaow-Lab/RUT-Bench", "url": "https://huggingface.co/papers/2606.03318"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Miaow-Lab/RUT-Bench.", "url": "https://arxiv.org/abs/2606.03318"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Miaow-Lab/RUT-Bench", "url": "https://arxiv.org/abs/2606.03318"}], "scope": "benchmark_repo", "url": "https://github.com/Miaow-Lab/RUT-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_rut-bench_450993d2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Miaow-Lab/RUT-Bench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.03318", "paper": "https://arxiv.org/abs/2606.03318", "pdf": "https://arxiv.org/pdf/2606.03318", "project": null, "report": "https://arxiv.org/abs/2606.03318"}, "metrics": [], "motivation": "Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios.", "name": "RUT-Bench", "oneLine": "RUT-Bench evaluates LLM tool-use in realistic user interactions with 1,638 test samples across 59 executable environments, measuring success rate, informational honesty, and tool discipline.", "paperTitle": "Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.03318", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Miaow-Lab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Miaow-Lab/RUT-Bench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Xuan Yang", "Hao Xu", "Tingfeng Hui", "Hongsheng Xin", "Kaike Zhang", "Chunxiao Liu", "Ning Miao"], "categories": ["cs.CL"], "id": "2606.03318", "title": "Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03318"}, "sourceUpdatedAt": "2026-06-03T03:19:48Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Fill the gap of real-world tool-calling evaluation by simulating non-ideal user behaviors, providing a standardized framework for assessing LLM robustness in practical scenarios."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
