{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.03920", "kind": "paper", "url": "https://arxiv.org/abs/2607.03920"}], "authors": ["Rufeng Chen", "Yue Chang", "Zili Shao", "Zhaofan Zhang", "Li Chen", "Hechang Chen", "Hui Xiong", "Sihong Xie"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.03920", "source_url": "https://arxiv.org/abs/2607.03920"}, "categories": ["Robotics & Embodied AI", "cs.RO"], "description": {"en": "LH-AVLN is a benchmark for long-horizon navigation that combines multi-goal missions, heterogeneous goal specifications, and persistent spatialized audio cues. Agents must execute missions of two to four goals specified by category, language, or reference image, using RGB-D, pose, and binaural audio in indoor 3D environments. It supports ordered and unordered missions with alternating goal-associated sounds."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.03920", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.03920", "title": "LH-AVLN"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.03920", "modality": null, "name": "LH-AVLN", "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_lh-avln_cb4be7f0", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f1d4a2c8d890d47dfc3b5b8a77cd1d660b831480f590366690a2cdfcf8f94d16", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.03920"}, "publisher": null, "released": "2026-07-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.03920", "source_url": "https://arxiv.org/abs/2607.03920"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-03920", "source": "claire_radar", "source_benchmark_id": "2607.03920", "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/2607.03920", "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": [], "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": "980a8dd752a8b2cef97ca30f6aa3f5b1eeb18796d059e953b0118af450b16ed1", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "LH-AVLN is a benchmark for long-horizon navigation that combines multi-goal missions, heterogeneous goal specifications, and persistent spatialized audio cues. Agents must execute missions of two to four goals specified by category, language, or reference image, using RGB-D, pose, and binaural audio in indoor 3D environments. It supports ordered and unordered missions with alternating goal-associated sounds.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce LH-AVLN, a benchmark for Long-Horizon Audio-Visual-Language Navigation that combines multi-goal mission execution, heterogeneous goal specifications, and persistent spatialized acoustic cues."}, "familyId": "bmf_bd018386fef4", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_lh-avln_cb4be7f0", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.03920", "paper": "https://arxiv.org/abs/2607.03920", "pdf": "https://arxiv.org/pdf/2607.03920", "project": null, "report": "https://arxiv.org/abs/2607.03920"}, "metrics": [], "motivation": "Embodied navigation is moving toward long-horizon missions, yet existing long-horizon benchmarks are largely acoustically silent, and audio-visual navigation tasks typically focus on a single goal.", "name": "LH-AVLN", "oneLine": "LH-AVLN is a benchmark for long-horizon navigation that combines multi-goal missions, heterogeneous goal specifications, and persistent spatialized audio cues. Agents must execute missions of two to four goals specified by category, language, or reference image, using RGB-D, pose, and binaural audio in indoor 3D environments. It supports ordered and unordered missions with alternating goal-associated sounds.", "paperTitle": "LH-AVLN: A Benchmark for Long-Horizon Audio-Visual-Language Navigation", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.03920", "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": "2026-07-04", "source": {"authors": ["Rufeng Chen", "Yue Chang", "Zili Shao", "Zhaofan Zhang", "Li Chen", "Hechang Chen", "Hui Xiong", "Sihong Xie"], "categories": ["cs.RO"], "id": "2607.03920", "title": "LH-AVLN: A Benchmark for Long-Horizon Audio-Visual-Language Navigation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.03920"}, "sourceUpdatedAt": "2026-07-20T09:22:48Z", "topics": ["cs.RO"], "venueAttempts": [], "whyItMatters": "Existing navigation benchmarks do not integrate long-horizon missions with audio-visual cues and heterogeneous goal types, while audio-visual tasks are typically single-goal. LH-AVLN addresses this gap by providing a multi-goal environment with acoustic guidance and distractors, enabling more realistic evaluation of embodied agents in complex missions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
