{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.31251", "kind": "paper", "url": "https://arxiv.org/abs/2605.31251"}, {"id": "gh:kaixuewen/ergeobench", "kind": "repo", "url": "https://github.com/kaiXuewen/ERGeoBench"}, {"kind": "website", "url": "https://kaixuewen.github.io/ERGeoBench/"}], "authors": ["Kaiwen Xue", "Tao Wei", "Guoxin Zhang", "Zhonghong Ou", "Kaoyan Lu", "Yu Feng", "Yifan Zhu", "Haoran Luo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.31251", "source_url": "https://arxiv.org/abs/2605.31251"}, "categories": ["Multimodal", "Reasoning", "Robotics & Embodied AI"], "description": {"en": "ERGeoBench evaluates vision-driven embodied geo-localization in MLLMs with 2,207 globally distributed street-view panoramas under single-view, panorama-view, and embodied-view settings. It measures foundational perception, spatial awareness, common sense reasoning, and geo-localization reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.31251", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.31251", "title": "ERGeoBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Beijing University of Posts and Telecommunications", "State Key Laboratory of Networking and Switching Technology", "Shanghai Jiao Tong University", "China Mobile Research Institute", "Nanyang Technological University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.31251", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.31251", "source_url": "https://openalex.org/W7163045470"}, "key": "claire-radar:2605.31251", "modality": null, "name": "ERGeoBench", "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_ergeobench_37de7936", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3e62384e7a6bcc551e8ac70a87a66d73c545b9ee4818f4fdac8565bd8515a7a1", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.31251"}, "publisher": null, "released": "2026-05-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.31251", "source_url": "https://arxiv.org/abs/2605.31251"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-31251", "source": "claire_radar", "source_benchmark_id": "2605.31251", "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": "https://github.com/kaiXuewen/ERGeoBench", "githubScope": "benchmark_repo", "githubStars": 12, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2605.31251", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "capabilities": ["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": "19f60e4b9df0eb40d3e7709010980223210ff749e827affe8ff9644b57c89eec", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ERGeoBench evaluates vision-driven embodied geo-localization in MLLMs with 2,207 globally distributed street-view panoramas under single-view, panorama-view, and embodied-view settings. It measures foundational perception, spatial awareness, common sense reasoning, and geo-localization reasoning.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce ERGeoBench, a diagnostic benchmark for vision-driven embodied geo-localization."}, "familyId": "bmf_323d61775db6", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/kaiXuewen/ERGeoBench", "url": "https://kaixuewen.github.io/ERGeoBench/"}], "scope": "benchmark_repo", "url": "https://github.com/kaiXuewen/ERGeoBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_ergeobench_37de7936", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/kaiXuewen/ERGeoBench", "data": null, "hfPaper": "https://huggingface.co/papers/2605.31251", "paper": "https://arxiv.org/abs/2605.31251", "pdf": "https://arxiv.org/pdf/2605.31251", "project": "https://kaixuewen.github.io/ERGeoBench/", "report": "https://arxiv.org/abs/2605.31251"}, "metrics": [], "motivation": "Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluation.", "name": "ERGeoBench", "oneLine": "ERGeoBench evaluates vision-driven embodied geo-localization in MLLMs with 2,207 globally distributed street-view panoramas under single-view, panorama-view, and embodied-view settings. It measures foundational perception, spatial awareness, common sense reasoning, and geo-localization reasoning.", "paperTitle": "ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.31251", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ERGeoBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://kaixuewen.github.io/ERGeoBench/"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-29", "source": {"authors": ["Kaiwen Xue", "Tao Wei", "Guoxin Zhang", "Zhonghong Ou", "Kaoyan Lu", "Yu Feng", "Yifan Zhu", "Haoran Luo"], "categories": ["cs.CV", "cs.AI"], "id": "2605.31251", "title": "ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2605.31251"}, "sourceUpdatedAt": "2026-05-29T12:49:17Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "Embodied geo-localization is underexplored due to lack of fine-grained evaluation. ERGeoBench provides a unified diagnostic framework that reveals current MLLMs struggle with fine-grained perceptual operations and metric localization, supporting progress in integrated perception and spatial reasoning."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
