{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.26623", "kind": "paper", "url": "https://arxiv.org/abs/2608.26623"}], "authors": ["Abhigya Verma", "Amit Kumar Saha", "Seganrasan Subramanian", "Sai Harshitha Aluru"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.26623", "source_url": "https://arxiv.org/abs/2608.26623"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely unexamined."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.26623", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.26623", "title": "AgentJudgeBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.26623", "modality": null, "name": "AgentJudgeBench", "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": "true", "origin_record_id": "bm_agentjudgebench_8ae8da3e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "cced5cd2bbbfe58c270a7fd6a819ad73d600eb09e88de8ba2a2edf6f3677bb8c", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.26623"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.26623", "source_url": "https://arxiv.org/abs/2608.26623"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-26623", "source": "claire_radar", "source_benchmark_id": "2608.26623", "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": 19, "hfPaperUrl": "https://huggingface.co/papers/2608.26623", "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": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present AgentJudgeBench, the first benchmark to systematically study LLM-as-a-judge reliability for agentic tool-calling over workflow DAGs, as distinct from the broader LLM-as-a-judge task of open-ended text or preference evaluation."}, "familyId": "bmf_cfd6a96e803e", "firstSeenAt": "2026-08-30", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_agentjudgebench_8ae8da3e", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.26623", "paper": "https://arxiv.org/abs/2608.26623", "pdf": "https://arxiv.org/pdf/2608.26623", "project": null, "report": "https://arxiv.org/abs/2608.26623"}, "metrics": [], "motivation": "LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely unexamined.", "name": "AgentJudgeBench", "oneLine": "LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely unexamined.", "paperTitle": "AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling", "primaryDomain": "General AI", "publication": {"evidence": "31 Pages, 9 Figures, 31 Tables, Accepted as a main conference paper at EMNLP 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.26623", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "as a main conference paper at EMNLP 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.5293297441967314, "value": 19}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 50}, "method": "attention-ranking-v13", "rank": null, "score": 50}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-27", "source": {"authors": ["Abhigya Verma", "Amit Kumar Saha", "Seganrasan Subramanian", "Sai Harshitha Aluru"], "categories": ["cs.AI"], "id": "2608.26623", "title": "AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling", "type": "arxiv", "url": "https://arxiv.org/abs/2608.26623"}, "sourceUpdatedAt": "2026-08-27T05:20:22Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "31 Pages, 9 Figures, 31 Tables, Accepted as a main conference paper at EMNLP 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "31 Pages, 9 Figures, 31 Tables, Accepted as a main conference paper at EMNLP 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.26623"}], "reviewStatus": "accepted", "venueName": "as a main conference paper at EMNLP 2026"}]}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
