{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.14379", "kind": "paper", "url": "https://arxiv.org/abs/2608.14379"}, {"id": "gh:lxroboticslab/reflexbench", "kind": "repo", "url": "https://github.com/LxRoboticsLab/ReflexBench"}, {"kind": "website", "url": "https://reflexvla.github.io"}], "authors": ["Yuxuan Chen", "Wanruo Zhang", "Xiao Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.14379", "source_url": "https://arxiv.org/abs/2608.14379"}, "categories": ["Multimodal", "Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "Evaluates vision-language-action models on reaction-critical manipulation across six dynamic tasks, with configurable latency under synchronous and asynchronous inference in a simulated environment."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.14379", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.14379", "title": "ReflexBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.14379", "modality": null, "name": "ReflexBench", "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_reflexbench_c4d78abf", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "636e272bc36bf226cce76ddfa15a0438fed592ce37e0c5972cbe7ecb9f2ad191", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.14379"}, "publisher": null, "released": "2026-08-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.14379", "source_url": "https://arxiv.org/abs/2608.14379"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-14379", "source": "claire_radar", "source_benchmark_id": "2608.14379", "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/LxRoboticsLab/ReflexBench", "githubScope": "benchmark_repo", "githubStars": 4, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.14379", "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": ["Robot manipulation"], "confidence": "High", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-21T04:30:40.934319Z", "inputHash": "bdc4d99df748d1c2299dff99899805226400fd6c05aa0524ede64b68926d761e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates vision-language-action models on reaction-critical manipulation across six dynamic tasks, with configurable latency under synchronous and asynchronous inference in a simulated environment.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we present ReflexBench, a benchmark for reaction-critical manipulation."}, "familyId": "bmf_0c3d9006dea6", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/LxRoboticsLab/ReflexBench", "url": "https://reflexvla.github.io"}], "scope": "benchmark_repo", "url": "https://github.com/LxRoboticsLab/ReflexBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_reflexbench_c4d78abf", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": "https://github.com/LxRoboticsLab/ReflexBench", "data": null, "hfPaper": "https://huggingface.co/papers/2608.14379", "paper": "https://arxiv.org/abs/2608.14379", "pdf": "https://arxiv.org/pdf/2608.14379", "project": "https://reflexvla.github.io", "report": "https://arxiv.org/abs/2608.14379"}, "metrics": [], "motivation": "Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation.", "name": "ReflexBench", "oneLine": "Evaluates vision-language-action models on reaction-critical manipulation across six dynamic tasks, with configurable latency under synchronous and asynchronous inference in a simulated environment.", "paperTitle": "Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.14379", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "ReflexVLA Project", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://reflexvla.github.io"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.21483102985913266, "value": 4}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 199, "score": 34}, "method": "attention-ranking-v13", "rank": 199, "score": 34}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-14", "source": {"authors": ["Yuxuan Chen", "Wanruo Zhang", "Xiao Li"], "categories": ["cs.RO", "cs.AI"], "id": "2608.14379", "title": "Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.14379"}, "sourceUpdatedAt": "2026-08-14T15:19:04Z", "topics": ["Robotics", "Multimodal"], "venueAttempts": [], "whyItMatters": "Addresses the lack of benchmarks for dynamic interaction scenarios in robotic manipulation, providing a standardized way to assess model performance under reaction-critical conditions."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
