{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.08402", "kind": "paper", "url": "https://arxiv.org/abs/2609.08402"}], "authors": ["Boao Yu", "Zimo Chen", "Junreng Rao", "Yue Hu", "Zhengqiu Zhu", "Yong Zhao", "Rusheng Ju"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.08402", "source_url": "https://arxiv.org/abs/2609.08402"}, "categories": ["Multimodal", "Robotics & Embodied AI"], "description": {"en": "AGOS-Bench evaluates VLMs on the urban Air-Ground Object Search task where a UAV and UGV coordinate to locate a target vehicle from multi-view visual references, reporting success rate and success weighted by path length."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.08402", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.08402", "title": "AGOS-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["National University of Defense Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.08402", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.08402", "source_url": "https://openalex.org/W7212032263"}, "key": "claire-radar:2609.08402", "modality": null, "name": "AGOS-Bench", "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": "false", "origin_record_id": "bm_agos-bench_29c4a49d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "86ddae28311ba63f860b7fac8f7ce6b672e6e99f527a788ba50887048a4647f6", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-09T06:27:57.312318Z", "source_url": "https://arxiv.org/abs/2609.08402"}, "publisher": null, "released": "2026-09-08", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.08402", "source_url": "https://arxiv.org/abs/2609.08402"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-08402", "source": "claire_radar", "source_benchmark_id": "2609.08402", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "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/2609.08402", "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 first dedicated benchmark for embodied air-ground cooperation and comprehensive evaluation of popular VLMs is likely to attract research community interest.", "score": 63}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T06:27:57.312318Z", "inputHash": "8726ed0b62a4e5949e74db35e8b21abf7352721f8691547c419e93978e442eee", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "Although the paper describes a benchmark with evaluation metrics, it provides no explicit evidence of public release of task inputs, evaluator, or submission path, making it impossible to confirm external reuse.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-09T06:27:57.312318Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AGOS-Bench evaluates VLMs on the urban Air-Ground Object Search task where a UAV and UGV coordinate to locate a target vehicle from multi-view visual references, reporting success rate and success weighted by path length.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To study this underexplored problem, we introduce AGOS-Bench, the first dedicated benchmark for evaluating whether general-purpose Vision-Language Models (VLMs) can integrate aerial discoveries and ground-level verification through UAV-UGV cooperation."}, "familyId": "bmf_827b4e396296", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_agos-bench_29c4a49d", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.08402", "pdf": "https://arxiv.org/pdf/2609.08402", "project": null, "report": "https://arxiv.org/abs/2609.08402"}, "metrics": [], "motivation": "Air-Ground Object Search (AGOS) in urban environments is a challenging embodied task, which requires an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV) to jointly search for and verify a specified target vehicle from multi-view visual references.", "name": "AGOS-Bench", "oneLine": "AGOS-Bench evaluates VLMs on the urban Air-Ground Object Search task where a UAV and UGV coordinate to locate a target vehicle from multi-view visual references, reporting success rate and success weighted by path length.", "paperTitle": "Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.08402", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "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}, "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": "2026-09-08", "source": {"authors": ["Boao Yu", "Zimo Chen", "Junreng Rao", "Yue Hu", "Zhengqiu Zhu", "Yong Zhao", "Rusheng Ju"], "categories": ["cs.CV", "cs.AI"], "id": "2609.08402", "title": "Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method", "type": "arxiv", "url": "https://arxiv.org/abs/2609.08402"}, "sourceUpdatedAt": "2026-09-08T08:13:00Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "It provides the first standardized evaluation for air-ground cooperative embodied object search, enabling systematic comparison of vision-language model capabilities in complex multi-agent urban environments."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
