{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24526", "kind": "paper", "url": "https://arxiv.org/abs/2606.24526"}], "authors": ["Honglin Guo", "Qi Zhang", "Yu Zhang", "Weijie Li", "Rui Zheng", "Zhikai Lei", "Qiyuan Peng", "Zhiheng Xi", "Tao Gui", "Qi Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24526", "source_url": "https://arxiv.org/abs/2606.24526"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "Agora evaluates agentic document reasoning across eight domain collections of 9,664 authentic workplace documents. It includes 362 questions requiring location of sparse evidence and reconciliation of terminology, units, and time conventions. The benchmark is designed to exceed model context windows, necessitating deliberate exploration."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24526", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24526", "title": "AGORA"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.24526", "modality": null, "name": "AGORA", "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_agora_fee07ca2", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f4d125add3d5b7947852ab4db6d5b0155e79cf9737dbae3c7d62cb2cdea791bf", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24526"}, "publisher": null, "released": "2026-06-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24526", "source_url": "https://arxiv.org/abs/2606.24526"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24526", "source": "claire_radar", "source_benchmark_id": "2606.24526", "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": 6, "hfPaperUrl": "https://huggingface.co/papers/2606.24526", "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": "2026-10-04", "state": "stale"}}, "status": "stale"}, "capabilities": ["Reasoning"], "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": "78100f1519a9c322586b53a6b603f591e87a8da3920f7d645914a49eb2abf118", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Agora evaluates agentic document reasoning across eight domain collections of 9,664 authentic workplace documents. It includes 362 questions requiring location of sparse evidence and reconciliation of terminology, units, and time conventions. The benchmark is designed to exceed model context windows, necessitating deliberate exploration.", "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"], "snippet": "We introduce Agora, a benchmark pairing 362 questions with eight domain collections of 9,664 authentic documents and 372M tokens, far exceeding any model's context window, so agents must explore deliberately rather than scan exhaustively."}, "familyId": "bmf_f7070d57bbe5", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_agora_fee07ca2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.24526", "paper": "https://arxiv.org/abs/2606.24526", "pdf": "https://arxiv.org/pdf/2606.24526", "project": null, "report": "https://arxiv.org/abs/2606.24526"}, "metrics": [], "motivation": "Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge.", "name": "AGORA", "oneLine": "Agora evaluates agentic document reasoning across eight domain collections of 9,664 authentic workplace documents. It includes 362 questions requiring location of sparse evidence and reconciliation of terminology, units, and time conventions. The benchmark is designed to exceed model context windows, necessitating deliberate exploration.", "paperTitle": "AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.24526", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "AGORA Benchmark Team", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.24526"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-23", "source": {"authors": ["Honglin Guo", "Qi Zhang", "Yu Zhang", "Weijie Li", "Rui Zheng", "Zhikai Lei", "Qiyuan Peng", "Zhiheng Xi", "Tao Gui", "Qi Zhang"], "categories": ["cs.CL"], "id": "2606.24526", "title": "AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24526"}, "sourceUpdatedAt": "2026-06-23T12:57:18Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Agora addresses the gap in evaluating archive-grounded reasoning where agents must navigate large, messy document collections. It provides a challenging and realistic testbed for assessing agentic document search and synthesis capabilities, offering practical insights for deployment in document-intensive domains."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
