{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2610.05414", "kind": "paper", "url": "https://arxiv.org/abs/2610.05414"}, {"kind": "website", "url": "https://mxxq-stack.github.io/rmmbench-project/"}], "authors": ["Huapeng Li", "Fuxiang Feng", "Jinqiu Fan", "Shuo Yang", "Fengjiao Chen", "Xuezhi Cao", "Ran Song", "Wei Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2610.05414", "source_url": "https://arxiv.org/abs/2610.05414"}, "categories": ["Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "Although the advancement of vision-language models (VLMs) has endowed robots with enhanced environmental understanding and task reasoning, a comprehensive evaluation methodology is important to advance the integration of VLMs in robotic na…"}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2610.05414", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2610.05414", "title": "RMMBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2610.05414", "modality": null, "name": "RMMBench", "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": "true", "origin_record_id": "bm_rmmbench_5c56f9de", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d7ea164c2e0d453334444aa5e21b7975ebae434a74f3df829b65b4b61d8e683c", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-10-07T07:29:11.066253Z", "source_url": "https://arxiv.org/abs/2610.05414"}, "publisher": null, "released": "2026-10-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2610.05414", "source_url": "https://arxiv.org/abs/2610.05414"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2610-05414", "source": "claire_radar", "source_benchmark_id": "2610.05414", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "capabilities": ["Robot manipulation"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-10-07T07:29:11.066253Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this issue, we propose RMMBench, an evaluation benchmark that requires robots to understand language instructions and perform long-horizon tasks in continuous spaces."}, "familyId": "bmf_63ab8ca12467", "firstSeenAt": "2026-10-06", "heat": null, "id": "bm_rmmbench_5c56f9de", "indexedAt": "2026-10-07T07:28:43.628712Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2610.05414", "pdf": "https://arxiv.org/pdf/2610.05414", "project": "https://mxxq-stack.github.io/rmmbench-project/", "report": "https://arxiv.org/abs/2610.05414"}, "metrics": [], "motivation": "Although the advancement of vision-language models (VLMs) has endowed robots with enhanced environmental understanding and task reasoning, a comprehensive evaluation methodology is important to advance the integration of VLMs in robotic navigation and manipulation.", "name": "RMMBench", "oneLine": "Although the advancement of vision-language models (VLMs) has endowed robots with enhanced environmental understanding and task reasoning, a comprehensive evaluation methodology is important to advance the integration of VLMs in robotic na…", "paperTitle": "RMMBench: A Comprehensive Benchmark for Robotic Mobile Manipulation", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": "Accepted to the Conference on Robot Learning (CoRL 2026), November 9-12, 2026, Austin, TX, USA", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2610.05414", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "Conference on Robot Learning (CoRL 2026), November 9-12, 2026, Austin, TX, USA", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-10-04", "source": {"authors": ["Huapeng Li", "Fuxiang Feng", "Jinqiu Fan", "Shuo Yang", "Fengjiao Chen", "Xuezhi Cao", "Ran Song and Wei Zhang"], "categories": ["cs.RO"], "id": "2610.05414", "title": "RMMBench: A Comprehensive Benchmark for Robotic Mobile Manipulation", "type": "arxiv", "url": "https://arxiv.org/abs/2610.05414"}, "sourceUpdatedAt": "2026-10-04T17:55:26Z", "topics": ["Robotics"], "venueAttempts": [{"decisionRaw": "Accepted to the Conference on Robot Learning (CoRL 2026), November 9-12, 2026, Austin, TX, USA", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to the Conference on Robot Learning (CoRL 2026), November 9-12, 2026, Austin, TX, USA", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2610.05414"}], "reviewStatus": "accepted", "venueName": "Conference on Robot Learning (CoRL 2026), November 9-12, 2026, Austin, TX, USA"}]}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
