{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.22014", "kind": "paper", "url": "https://arxiv.org/abs/2607.22014"}], "authors": ["Suman Navaratnarajah", "Taehyoung Kim", "Jona Ruthardt", "Ishaan Bhimwal", "Ryousuke Yamada", "Yannik Blei", "Wolfram Burgard", "Yuki M Asano"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.22014", "source_url": "https://arxiv.org/abs/2607.22014"}, "categories": ["Geometric reasoning", "Robotics & Embodied AI", "Vision & 3D", "cs.AI"], "description": {"en": "A benchmark for mission-level evaluation of MLLMs in aerial 3D environments, consisting of 120 missions across five simulated environments and four task families."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.22014", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.22014", "title": "MissionBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.22014", "modality": null, "name": "MissionBench", "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_missionbench_cc95e3a2", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e18b9b2ca4a3fb46046a45f4668e30e8a16815e161f1eab221136bc7eb1e6e12", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.22014"}, "publisher": null, "released": "2026-07-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.22014", "source_url": "https://arxiv.org/abs/2607.22014"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-22014", "source": "claire_radar", "source_benchmark_id": "2607.22014", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Vision & 3D", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2607.22014", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Geometric reasoning"], "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": "0f2dbb9535534373f1396007bf234da9f9e3d2e467a1c29ae7ffaa72d8c2bfdb", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark for mission-level evaluation of MLLMs in aerial 3D environments, consisting of 120 missions across five simulated environments and four task families.", "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 introduce MissionBench, a benchmark for mission-level evaluation of MLLMs in aerial 3D environments."}, "familyId": "bmf_a4dfacf50588", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_missionbench_cc95e3a2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.22014", "paper": "https://arxiv.org/abs/2607.22014", "pdf": "https://arxiv.org/pdf/2607.22014", "project": null, "report": "https://arxiv.org/abs/2607.22014"}, "metrics": [], "motivation": "Multimodal Large Language Models (MLLMs) are emerging as core reasoning modules for embodied agents, yet it remains unclear how well general-purpose models can solve long-horizon embodied tasks from a single high-level instruction.", "name": "MissionBench", "oneLine": "A benchmark for mission-level evaluation of MLLMs in aerial 3D environments, consisting of 120 missions across five simulated environments and four task families.", "paperTitle": "Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.22014", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-24", "source": {"authors": ["Suman Navaratnarajah", "Taehyoung Kim", "Jona Ruthardt", "Ishaan Bhimwal", "Ryousuke Yamada", "Yannik Blei", "Wolfram Burgard", "Yuki M Asano"], "categories": ["cs.AI", "cs.CL", "cs.CV", "cs.RO"], "id": "2607.22014", "title": "Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2607.22014"}, "sourceUpdatedAt": "2026-07-24T06:22:50Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Highlights the difficulty of zero-shot long-horizon embodied tasks and the need for closed-loop evaluation, motivating scaling-driven improvements."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
