{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.06346", "kind": "paper", "url": "https://arxiv.org/abs/2608.06346"}], "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "Evaluates critical error detection in long-horizon agent trajectories using 486 annotated failed trajectories with error lifecycle labels."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.06346", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.06346", "title": "TrajErrBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.06346", "modality": null, "name": "TrajErrBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_trajerrbench_f533923d", "origin_source": "arxiv", "recognition_confidence": "0.5", "record_sha256": "52755958d0daa1b519864afc7eda69247aebcca2fcdc74784d07ffaf35c23522", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-06T08:45:23.913416Z", "source_url": "https://arxiv.org/abs/2608.06346"}, "publisher": null, "released": "2026-08-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.06346", "source_url": "https://arxiv.org/abs/2608.06346"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-06346", "source": "claire_radar", "source_benchmark_id": "2608.06346", "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/2608.06346", "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"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The agent debugging focus and explicit benchmark release are likely to draw moderate interest from the agent evaluation community.", "score": 45}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-06T08:45:23.913416Z", "inputHash": "936dbdc237479d757144723c0e0be86a21b6e2bf08e65c2987699e61254e123d", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We further construct TrajErrBench, a benchmark of 486 manually annotated failed trajectories", "canonicalNameSource": "abstract", "decisionReason": "Explicitly constructs and names a benchmark with manual annotations and promises release of codes and data.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-06T08:45:23.913416Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates critical error detection in long-horizon agent trajectories using 486 annotated failed trajectories with error lifecycle labels.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "We further construct TrajErrBench, a benchmark of 486 manually annotated failed trajectories from Tau2Bench and SWE-Bench Pro, covering realistic tool-use and coding scenarios."}, "familyId": "bmf_301cdf182b45", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_trajerrbench_f533923d", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.06346", "pdf": "https://arxiv.org/pdf/2608.06346", "project": null, "report": "https://arxiv.org/abs/2608.06346"}, "metrics": [], "motivation": "LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging.", "name": "TrajErrBench", "oneLine": "Evaluates critical error detection in long-horizon agent trajectories using 486 annotated failed trajectories with error lifecycle labels.", "paperTitle": "TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.06346", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "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": 0.5, "relation": "evaluates_only", "releasedAt": "2026-08-06", "source": {"authors": ["Yunjia Qi", "Zehua Yin", "Xintong Shi", "Hao Peng", "Songyuanyi Lu", "Yixian Liu", "Richeng Xuan", "Yuhong Liu", "Zhichao Hu", "Xiaozhi Wang", "Lei Hou", "Bin Xu", "Juanzi Li"], "categories": ["cs.AI"], "id": "2608.06346", "title": "TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories", "type": "arxiv", "url": "https://arxiv.org/abs/2608.06346"}, "sourceUpdatedAt": "2026-08-06T17:51:20Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Provides a focused resource for debugging cascading failures in agents, with planned code and data release supporting reproducibility."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
