{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.11070", "kind": "paper", "url": "https://arxiv.org/abs/2606.11070"}], "authors": ["Genta Indra Winata", "Amartya Chakraborty", "Yuzhen Lin", "Swasthi P Rao", "Shikhhar Siingh", "Houhan Lu", "Nadia Bathaee", "Sriharsha Hatwar", "Paresh Dashore", "Anmol Jain", "Kshitij Tayal", "Xiuzhu Lin", "Anirban Das", "Sambit Sahu", "Shi-Xiong Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.11070", "source_url": "https://arxiv.org/abs/2606.11070"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "T1-Bench evaluates agentic systems through realistic customer-facing, multi-domain tasks. Scenarios involve multi-turn user-assistant interactions across 25 domains with varying difficulty, measuring structured reasoning, tool utilization, and conversational quality. Automatic evaluation is complemented by human judgments."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.11070", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.11070", "title": "T1-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.11070", "modality": null, "name": "T1-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_t1-bench_01df3d35", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e2e1515633096751fddd4bdfda3127b13b735383b69876610a4e7a7ee2b81cfb", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.11070"}, "publisher": null, "released": "2026-06-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.11070", "source_url": "https://arxiv.org/abs/2606.11070"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-11070", "source": "claire_radar", "source_benchmark_id": "2606.11070", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.11070", "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", "lastSuccessfulDate": "2026-09-24", "state": "stale"}}, "status": "stale"}, "capabilities": ["Reasoning"], "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": "6398f5c4a2cce8c21857c40b86c8bd3ca282bc018316f5e2ee279296e0b20e33", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "T1-Bench evaluates agentic systems through realistic customer-facing, multi-domain tasks. Scenarios involve multi-turn user-assistant interactions across 25 domains with varying difficulty, measuring structured reasoning, tool utilization, and conversational quality. Automatic evaluation is complemented by human judgments.", "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 these limitations, we introduce T1-Bench, a high-fidelity, comprehensive benchmark for evaluating agentic systems in realistic customer-facing, multi-domain environments, featuring interleaved scenarios that require structured reasoning across multi-turn user-assistant interactions and substantially increasing both compositional complexity and evaluative rigor across 25 domains of varying difficulty."}, "familyId": "bmf_dbcfe3a64553", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_t1-bench_01df3d35", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.11070", "paper": "https://arxiv.org/abs/2606.11070", "pdf": "https://arxiv.org/pdf/2606.11070", "project": null, "report": "https://arxiv.org/abs/2606.11070"}, "metrics": [], "motivation": "Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems.", "name": "T1-Bench", "oneLine": "T1-Bench evaluates agentic systems through realistic customer-facing, multi-domain tasks. Scenarios involve multi-turn user-assistant interactions across 25 domains with varying difficulty, measuring structured reasoning, tool utilization, and conversational quality. Automatic evaluation is complemented by human judgments.", "paperTitle": "T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.11070", "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": "2026-06-09", "source": {"authors": ["Genta Indra Winata", "Amartya Chakraborty", "Yuzhen Lin", "Swasthi P Rao", "Shikhhar Siingh", "Houhan Lu", "Nadia Bathaee", "Sriharsha Hatwar", "Paresh Dashore", "Anmol Jain", "Kshitij Tayal", "Xiuzhu Lin", "Anirban Das", "Sambit Sahu", "Shi-Xiong Zhang"], "categories": ["cs.CL", "cs.AI"], "id": "2606.11070", "title": "T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains", "type": "arxiv", "url": "https://arxiv.org/abs/2606.11070"}, "sourceUpdatedAt": "2026-06-09T16:32:14Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Existing agent benchmarks lack realism and domain diversity, limiting assessment of sustained multi-step reasoning. T1-Bench addresses this gap by providing interleaved, complex scenarios across multiple domains, enabling more accurate evaluation of agents' practical capabilities in real-world customer service settings."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
