{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.28266", "kind": "paper", "url": "https://arxiv.org/abs/2608.28266v1"}], "authors": ["Yang Chen", "Ye-Xin Xie", "Lirong Che", "Danyang Peng", "Yuzhe Yang", "Peiwen Lin", "Xu Cao", "Chuang Wang", "Lei Yuan", "Jian Su", "Lan-Zhe Guo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.28266", "source_url": "https://arxiv.org/abs/2608.28266"}, "categories": ["Agents", "Planning", "Robotics & Embodied AI"], "description": {"en": "Construct-level benchmark with 897 oracle-validated household task instances evaluating four coordination constructs (allocation, ordering, mutual exclusion, handoff) via task success and construct-level scores."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.28266v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.28266v1", "title": "CoCoBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Nanjing University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.28266", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.28266", "source_url": "https://openalex.org/W7204768814"}, "key": "claire-radar:2608.28266", "modality": null, "name": "CoCoBench", "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": "false", "origin_record_id": "bm_cocobench_0d6f9f05", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "45306249e699ae4080ca850d44150b02fe109dac11cf0d2bb0896ed60775310c", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-06T08:46:12.648160Z", "source_url": "https://arxiv.org/abs/2608.28266v1"}, "publisher": null, "released": "2026-08-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.28266", "source_url": "https://arxiv.org/abs/2608.28266v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-28266", "source": "claire_radar", "source_benchmark_id": "2608.28266", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "attention": {"asOf": "2026-09-06", "attemptedAt": "2026-09-06T01:30:14.942019Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.28266", "observedAt": "2026-09-05T06:23:21.096343Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-06T01:30:14.942019Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Multi-agent coordination is an active area, but the absence of a repository or dataset link and a relatively narrow construct-level focus limit early visibility.", "score": 30}, "capabilities": ["Planning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-06T08:46:12.648160Z", "inputHash": "c28bd74bb3ba32c6d5fb3b3388368fe852962d4fd961c872e50da83a7ce32d65", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "No public artifact link is supplied, and the paper does not state a release; without a code or data path, the benchmark cannot currently be reused by others.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-06T08:46:12.648160Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Construct-level benchmark with 897 oracle-validated household task instances evaluating four coordination constructs (allocation, ordering, mutual exclusion, handoff) via task success and construct-level scores.", "displayEligible": false, "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"], "snippet": "In this paper, we introduce CoCoBench, a construct-level benchmark for evaluating multi-agent embodied coordination in executable household tasks."}, "familyId": "bmf_75548b7ea87a", "firstSeenAt": "2026-08-31", "heat": null, "id": "bm_cocobench_0d6f9f05", "indexedAt": "2026-08-31T07:22:53.604319Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.28266", "paper": "http://arxiv.org/abs/2608.28266v1", "pdf": "https://arxiv.org/pdf/2608.28266v1", "project": null, "report": "http://arxiv.org/abs/2608.28266v1"}, "metrics": [], "motivation": "Agent systems powered by multimodal large language models (MLLMs) have advanced rapidly in recent years, yet existing embodied-agent benchmarks still lack fine-grained diagnostics for multi-agent coordination.", "name": "CoCoBench", "oneLine": "Construct-level benchmark with 897 oracle-validated household task instances evaluating four coordination constructs (allocation, ordering, mutual exclusion, handoff) via task success and construct-level scores.", "paperTitle": "CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.28266v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-06T06:14:00.513894Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-28", "source": {"authors": ["Yang Chen", "Ye-Xin Xie", "Lirong Che", "Danyang Peng", "Yuzhe Yang", "Peiwen Lin", "Xu Cao", "Chuang Wang", "Lei Yuan", "Jian Su", "Lan-Zhe Guo"], "categories": ["cs.RO"], "id": "2608.28266", "title": "CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning", "type": "arxiv", "url": "http://arxiv.org/abs/2608.28266v1"}, "sourceUpdatedAt": "2026-08-28T12:29:23Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Supplies fine-grained diagnostics for multi-agent coordination failures that overall success rates obscure, potentially guiding targeted improvements in embodied multi-agent systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
