{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05793", "kind": "paper", "url": "https://arxiv.org/abs/2606.05793"}], "authors": ["Hong Qian", "Yuanhao Liu", "Zihan Zhou", "Zongbao Zhang", "Hanjie Ge", "Haotian Shi", "Liang Dou", "Xiangfeng Wang", "Jingwen Yang", "Aimin Zhou"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05793", "source_url": "https://arxiv.org/abs/2606.05793"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates collaborative ability of LLM agents in cooperative game environments with diverse player profiles and proactive engagement."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05793", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05793", "title": "CollabBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.05793", "modality": null, "name": "CollabBench", "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_collabbench_1ee76547", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e30b13ac567189af245df92ddeaeeb5202562c41889b07b57f064c0fefdf00ba", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05793"}, "publisher": null, "released": "2026-06-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05793", "source_url": "https://arxiv.org/abs/2606.05793"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05793", "source": "claire_radar", "source_benchmark_id": "2606.05793", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.05793", "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", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "stale"}, "capabilities": [], "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": "59de895f03c1c23e27dbc550f2dfb294b8b32d5fd9f3abca9175eb43f1e09df2", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates collaborative ability of LLM agents in cooperative game environments with diverse player profiles and proactive engagement.", "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"], "snippet": "To this end, this paper proposes CollabBench, a benchmark for evaluating and training collaborative agents in cooperative games."}, "familyId": "bmf_85f88426d607", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_collabbench_1ee76547", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.05793", "paper": "https://arxiv.org/abs/2606.05793", "pdf": "https://arxiv.org/pdf/2606.05793", "project": null, "report": "https://arxiv.org/abs/2606.05793"}, "metrics": [], "motivation": "While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging.", "name": "CollabBench", "oneLine": "Evaluates collaborative ability of LLM agents in cooperative game environments with diverse player profiles and proactive engagement.", "paperTitle": "CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement", "primaryDomain": "General AI", "publication": {"evidence": "Accepted by ICML 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.05793", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ICML 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-04", "source": {"authors": ["Hong Qian", "Yuanhao Liu", "Zihan Zhou", "Zongbao Zhang", "Hanjie Ge", "Haotian Shi", "Liang Dou", "Xiangfeng Wang", "Jingwen Yang", "Aimin Zhou"], "categories": ["cs.CL", "cs.AI", "cs.CY", "cs.LG"], "id": "2606.05793", "title": "CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05793"}, "sourceUpdatedAt": "2026-06-04T07:22:44Z", "topics": ["cs.CL"], "venueAttempts": [{"decisionRaw": "Accepted by ICML 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted by ICML 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.05793"}], "reviewStatus": "accepted", "venueName": "ICML 2026"}], "whyItMatters": "Could fill gap in grounded collaborative benchmarks, but lacks public evidence of evaluation protocol or artifacts."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
