{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01046", "kind": "paper", "url": "https://arxiv.org/abs/2606.01046"}], "authors": ["Weiyi Chen", "Shuaixiong Wang", "Ziyun Gao", "Kaichun Hu", "Wangze Ni", "Shimin Di", "Chen Jason Zhang", "Lei Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01046", "source_url": "https://arxiv.org/abs/2606.01046"}, "categories": ["General AI", "Language & Knowledge", "Planning", "cs.AI"], "description": {"en": "TravelEval evaluates LLM-powered travel planning agents in a realistic sandbox with accommodation pricing and intercity transport data, using six dimensions: accuracy, compliance, temporality, spatiality, economy, and utility. It simulates complete plans with API-integrated geographic information and queuing time."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01046", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01046", "title": "TravelEval"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.01046", "modality": null, "name": "TravelEval", "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_traveleval_64e034c5", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "86383fb52715177b44cb2c0f39af3c60943061eb713bb771bf1d35444cdec6ba", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01046"}, "publisher": null, "released": "2026-05-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01046", "source_url": "https://arxiv.org/abs/2606.01046"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01046", "source": "claire_radar", "source_benchmark_id": "2606.01046", "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/2606.01046", "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": ["Planning"], "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": "7a91bfc7574eee24a3fb9131e510d2ff6b23b941211c46e5635638b2fdcb83ce", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "TravelEval evaluates LLM-powered travel planning agents in a realistic sandbox with accommodation pricing and intercity transport data, using six dimensions: accuracy, compliance, temporality, spatiality, economy, and utility. It simulates complete plans with API-integrated geographic information and queuing time.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "To address this gap, we introduce TravelEval, a realistic and comprehensive benchmark."}, "familyId": "bmf_281eeec52056", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_traveleval_64e034c5", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.01046", "paper": "https://arxiv.org/abs/2606.01046", "pdf": "https://arxiv.org/pdf/2606.01046", "project": null, "report": "https://arxiv.org/abs/2606.01046"}, "metrics": [], "motivation": "The development of Large Language Models (LLMs) has significantly improved travel planning applications, yet evaluating such models is limited by existing benchmarks' limitations: 1) overemphasis on constraint compliance, neglecting multi-dimensional qualities like spatio-temporal cost; 2) datasets lacking real-world authenticity and coverage in key areas (e.g., lodging, transport); and 3) isolated daily plan assess…", "name": "TravelEval", "oneLine": "TravelEval evaluates LLM-powered travel planning agents in a realistic sandbox with accommodation pricing and intercity transport data, using six dimensions: accuracy, compliance, temporality, spatiality, economy, and utility. It simulates complete plans with API-integrated geographic information and queuing time.", "paperTitle": "TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning Agents", "primaryDomain": "General AI", "publication": {"evidence": "31pages, 8 figures, accepted by KDD 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.01046", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "KDD 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-31", "source": {"authors": ["Weiyi Chen", "Shuaixiong Wang", "Ziyun Gao", "Kaichun Hu", "Wangze Ni", "Shimin Di", "Chen Jason Zhang", "Lei Chen"], "categories": ["cs.AI"], "id": "2606.01046", "title": "TravelEval: A Comprehensive Benchmarking Framework for Evaluating LLM-Powered Travel Planning Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01046"}, "sourceUpdatedAt": "2026-05-31T06:29:19Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "31pages, 8 figures, accepted by KDD 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "31pages, 8 figures, accepted by KDD 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.01046"}], "reviewStatus": "accepted", "venueName": "KDD 2026"}], "whyItMatters": "Existing travel planning benchmarks overemphasize constraint compliance, lack real-world data coverage, and miss global plan quality. TravelEval offers a multi-dimensional framework to compare agent planning capabilities, aiding model selection for complex travel tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
