{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.26396", "kind": "paper", "url": "https://arxiv.org/abs/2605.26396"}, {"id": "gh:creativitybench/mm-creativitybench", "kind": "repo", "url": "https://github.com/CreativityBench/MM-CreativityBench"}], "authors": ["Cheng Qian", "Hyeonjeong Ha", "Jiayu Liu", "Jeonghwan Kim", "Emre Can Acikgoz", "Bingxuan Li", "Kunlun Zhu", "Jiateng Liu", "Aditi Tiwari", "Zhenhailong Wang", "Xiusi Chen", "Mahdi Namazifar", "Heng Ji"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.26396", "source_url": "https://arxiv.org/abs/2605.26396"}, "categories": ["Agents", "Agents & Tool Use", "General AI", "Multimodal", "Tool use"], "description": {"en": "MM-CreativityBench evaluates large multimodal models on affordance-grounded creative tool use, requiring scene inspection, entity/part selection, and physically feasible solutions in visually rich environments."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.26396", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.26396", "title": "MM-CreativityBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.26396", "modality": null, "name": "MM-CreativityBench", "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_mm-creativitybench_e366f23e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3ede4e221bf5f5505ace7a9edcf74c21719fc53b3a4a1ddc226f3e8fcd071c5f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.26396"}, "publisher": null, "released": "2026-05-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.26396", "source_url": "https://arxiv.org/abs/2605.26396"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-26396", "source": "claire_radar", "source_benchmark_id": "2605.26396", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/CreativityBench/MM-CreativityBench", "githubScope": "benchmark_repo", "githubStars": 5, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 18, "hfPaperUrl": "https://huggingface.co/papers/2605.26396", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Tool use"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d54abdaedabbfb3704140577574bd4b6c6df625f528f74f7076565e78c9f6678", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MM-CreativityBench evaluates large multimodal models on affordance-grounded creative tool use, requiring scene inspection, entity/part selection, and physically feasible solutions in visually rich environments.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To evaluate this ability, we introduce MM-CreativityBench, a benchmark for affordance-grounded creative tool use in visually rich, physically constrained environments."}, "familyId": "bmf_534ca0e1c4b9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/CreativityBench/MM-CreativityBench", "url": "https://github.com/CreativityBench/MM-CreativityBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/CreativityBench/MM-CreativityBench", "url": "https://huggingface.co/papers/2605.26396"}], "scope": "benchmark_repo", "url": "https://github.com/CreativityBench/MM-CreativityBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_mm-creativitybench_e366f23e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/CreativityBench/MM-CreativityBench", "data": null, "hfPaper": "https://huggingface.co/papers/2605.26396", "paper": "https://arxiv.org/abs/2605.26396", "pdf": "https://arxiv.org/pdf/2605.26396", "project": null, "report": "https://arxiv.org/abs/2605.26396"}, "metrics": [], "motivation": "Large multimodal models (LMMs) have rapidly advanced in perception and reasoning; however, it remains unclear whether these capabilities generalize to discovering visually grounded solutions in open-ended environments, beyond pattern recognition.", "name": "MM-CreativityBench", "oneLine": "MM-CreativityBench evaluates large multimodal models on affordance-grounded creative tool use, requiring scene inspection, entity/part selection, and physically feasible solutions in visually rich environments.", "paperTitle": "Advancing Creative Physical Intelligence in Large Multimodal Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.26396", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "MM-CreativityBench team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/CreativityBench/MM-CreativityBench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-25", "source": {"authors": ["Cheng Qian", "Hyeonjeong Ha", "Jiayu Liu", "Jeonghwan Kim", "Emre Can Acikgoz", "Bingxuan Li", "Kunlun Zhu", "Jiateng Liu", "Aditi Tiwari", "Zhenhailong Wang", "Xiusi Chen", "Mahdi Namazifar", "Heng Ji"], "categories": ["cs.AI", "cs.CL", "cs.LG"], "id": "2605.26396", "title": "Advancing Creative Physical Intelligence in Large Multimodal Models", "type": "arxiv", "url": "https://arxiv.org/abs/2605.26396"}, "sourceUpdatedAt": "2026-05-29T07:01:08Z", "topics": ["Agents", "Multimodal"], "venueAttempts": [], "whyItMatters": "It probes beyond pattern recognition, assessing grounded exploration and reasoning. Current models show gaps in exploration and hallucination, motivating preference-based alignment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
