{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.14680", "kind": "paper", "url": "https://arxiv.org/abs/2608.14680"}], "authors": ["Chenkai Zhang", "Yiran Li", "Yifang Tian", "Michalis Bachras", "Hans-Arno Jacobsen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.14680", "source_url": "https://arxiv.org/abs/2608.14680"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "AGENTCHAOSBENCH is a dataset of sanitized execution traces from five agentic applications with injected runtime faults, used to evaluate fault detection and localization from telemetry."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.14680", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.14680", "title": "AGENTCHAOSBENCH"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Toronto"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.14680", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.14680", "source_url": "https://openalex.org/W7203713097"}, "key": "claire-radar:2608.14680", "modality": null, "name": "AGENTCHAOSBENCH", "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_agentchaosbench_3680a518", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d8fd82520305ed71992f74454c7f95a250f920a16fc845063b5de7f7862514c5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.14680"}, "publisher": null, "released": "2026-08-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.14680", "source_url": "https://arxiv.org/abs/2608.14680"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-14680", "source": "claire_radar", "source_benchmark_id": "2608.14680", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2608.14680", "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", "state": "unavailable"}}, "status": "unavailable"}, "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": "d8265f900a0f5fb1b712b381254c06eae813c895964a23a9b7412f07c0e9c5c4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AGENTCHAOSBENCH is a dataset of sanitized execution traces from five agentic applications with injected runtime faults, used to evaluate fault detection and localization from telemetry.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present AGENTCHAOSBENCH, a benchmark for detecting and localizing runtime faults in agentic systems from their execution telemetry."}, "familyId": "bmf_6edc4728dc4b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_agentchaosbench_3680a518", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.14680", "paper": "https://arxiv.org/abs/2608.14680", "pdf": "https://arxiv.org/pdf/2608.14680", "project": null, "report": "https://arxiv.org/abs/2608.14680"}, "metrics": [], "motivation": "Reliability in LLM-based agentic systems is a property of the whole execution (its tool calls, model calls, guardrails, and inter-agent messages), not of the final answer alone, yet evaluating only task outcomes reveals little about how or why a run fails.", "name": "AGENTCHAOSBENCH", "oneLine": "AGENTCHAOSBENCH is a dataset of sanitized execution traces from five agentic applications with injected runtime faults, used to evaluate fault detection and localization from telemetry.", "paperTitle": "When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.14680", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-04", "source": {"authors": ["Chenkai Zhang", "Yiran Li", "Yifang Tian", "Michalis Bachras", "and Hans-Arno Jacobsen"], "categories": ["cs.AI", "cs.SE"], "id": "2608.14680", "title": "When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry", "type": "arxiv", "url": "https://arxiv.org/abs/2608.14680"}, "sourceUpdatedAt": "2026-08-04T20:47:37Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Addresses runtime fault diagnosis in LLM agentic systems, offering a reproducible task for comparing diagnostic methods across tool and agent boundaries."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
