{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.14058", "kind": "paper", "url": "https://arxiv.org/abs/2606.14058"}], "authors": ["Zhiyuan Zhang", "Yanlun Peng", "Jianing Zhang", "Xianda Guo", "Zehan Huang", "Haoran Liu", "Qifeng Li", "Shaofeng Zhang", "Xiaosong Jia", "Junchi Yan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.14058", "source_url": "https://arxiv.org/abs/2606.14058"}, "categories": ["Autonomous Driving", "Robotics & Embodied AI", "cs.RO"], "description": {"en": "ReactSim-Bench evaluates reactive capability of behavior world model simulators in autonomous driving by decoupling agent and AV control, using collision, map, and kinematic metrics on 2,636 scenarios."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.14058", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.14058", "title": "ReactSim-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Jiao Tong University", "Great Wall Motors (China)", "Artificial Intelligence in Medicine (Canada)", "Fudan University", "Wuhan University", "University of Science and Technology of China"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.14058", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.14058", "source_url": "https://openalex.org/W7164860803"}, "key": "claire-radar:2606.14058", "modality": null, "name": "ReactSim-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_reactsim-bench_5401cd81", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "84fc9dde14178b9dafa2f29a635c16b98c68f270af805f728f1b400c9b1ca835", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.14058"}, "publisher": null, "released": "2026-06-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.14058", "source_url": "https://arxiv.org/abs/2606.14058"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-14058", "source": "claire_radar", "source_benchmark_id": "2606.14058", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Autonomous Driving"], "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/2606.14058", "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": "Medium", "construction": "Interactive Environment", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "9dd59cb24a0c58188de4590d7f9edced5b30bda4b5d859f8ff45e157eb2da664", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ReactSim-Bench evaluates reactive capability of behavior world model simulators in autonomous driving by decoupling agent and AV control, using collision, map, and kinematic metrics on 2,636 scenarios.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "In this work, we introduce ReactSim-Bench for evaluating the reactive capability of behavior world model simulation in autonomous driving."}, "familyId": "bmf_a6b25ed93a48", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_reactsim-bench_5401cd81", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Automotive"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.14058", "paper": "https://arxiv.org/abs/2606.14058", "pdf": "https://arxiv.org/pdf/2606.14058", "project": null, "report": "https://arxiv.org/abs/2606.14058"}, "metrics": [], "motivation": "Reactive capability is a key property of data-driven behavior world model simulators for autonomous driving simulation systems.", "name": "ReactSim-Bench", "oneLine": "ReactSim-Bench evaluates reactive capability of behavior world model simulators in autonomous driving by decoupling agent and AV control, using collision, map, and kinematic metrics on 2,636 scenarios.", "paperTitle": "ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving", "primaryDomain": "Autonomous Driving", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.14058", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-12", "source": {"authors": ["Zhiyuan Zhang", "Yanlun Peng", "Jianing Zhang", "Xianda Guo", "Zehan Huang", "Haoran Liu", "Qifeng Li", "Shaofeng Zhang", "Xiaosong Jia", "Junchi Yan"], "categories": ["cs.RO"], "id": "2606.14058", "title": "ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving", "type": "arxiv", "url": "https://arxiv.org/abs/2606.14058"}, "sourceUpdatedAt": "2026-06-12T03:11:06Z", "topics": ["cs.RO"], "venueAttempts": [], "whyItMatters": "Existing sim benchmarks don't directly measure whether simulated agents respond feasibly to novel AV behaviors; this benchmark fills that gap for safe simulation-based testing."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
