{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.13120", "kind": "paper", "url": "https://arxiv.org/abs/2606.13120"}], "authors": ["Yunhan Wang", "Jiaan Wang", "Lianzhe Huang", "Xianfeng Zeng", "Fandong Meng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.13120", "source_url": "https://arxiv.org/abs/2606.13120"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "EvoBrowseComp evaluates search agents on evolving knowledge with 800 contamination-free questions synthesized from live web traversal. The benchmark is designed to be regularly updated to prevent contamination."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.13120", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.13120", "title": "EvoBrowseComp"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.13120", "modality": null, "name": "EvoBrowseComp", "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_evobrowsecomp_ef2e05ce", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b9b2f7835e517ded32e8e1959fb593c0d834cbe5ba33c1422f0f58989bbb46a9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.13120"}, "publisher": null, "released": "2026-06-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.13120", "source_url": "https://arxiv.org/abs/2606.13120"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-13120", "source": "claire_radar", "source_benchmark_id": "2606.13120", "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": 4, "hfPaperUrl": "https://huggingface.co/papers/2606.13120", "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": "2026-10-01", "state": "stale"}}, "status": "stale"}, "capabilities": ["Factuality"], "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": "15444e18d15747256fc0896ef09365d4f74f1c087ba5ad1c72b655a0b2ccacd6", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EvoBrowseComp evaluates search agents on evolving knowledge with 800 contamination-free questions synthesized from live web traversal. The benchmark is designed to be regularly updated to prevent contamination.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "In this paper, we introduce EvoBrowseComp, an evolving benchmark of 400 English and 400 Chinese contamination-free complex questions synthesized via live-web traversal."}, "familyId": "bmf_482f8121203a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_evobrowsecomp_ef2e05ce", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.13120", "paper": "https://arxiv.org/abs/2606.13120", "pdf": "https://arxiv.org/pdf/2606.13120", "project": null, "report": "https://arxiv.org/abs/2606.13120"}, "metrics": [], "motivation": "Search Agents -- large language models augmented with search tools -- have intensified the need for future-proof evaluation benchmarks.", "name": "EvoBrowseComp", "oneLine": "EvoBrowseComp evaluates search agents on evolving knowledge with 800 contamination-free questions synthesized from live web traversal. The benchmark is designed to be regularly updated to prevent contamination.", "paperTitle": "EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.13120", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-11", "source": {"authors": ["Yunhan Wang", "Jiaan Wang", "Lianzhe Huang", "Xianfeng Zeng", "Fandong Meng"], "categories": ["cs.CL"], "id": "2606.13120", "title": "EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge", "type": "arxiv", "url": "https://arxiv.org/abs/2606.13120"}, "sourceUpdatedAt": "2026-06-11T09:48:32Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Static benchmarks suffer from contamination and memorization, obscuring genuine retrieval. EvoBrowseComp offers a dynamic, auto-updated evaluation, which is critical for measuring true browsing competence."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
