{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.21833", "kind": "paper", "url": "https://arxiv.org/abs/2608.21833v1"}], "authors": ["Kun Chen", "Haorong Hong", "Peizhong Gao", "Jianfeng Lin", "Tongxu Luo", "Yuxuan Xie", "Chenxu Liu", "Jieling He", "Zhongyuan Liu", "Zeno Zeng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.21833", "source_url": "https://arxiv.org/abs/2608.21833"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates coding agents across three game development lifecycle tracks: generation, bug diagnosis and repair, and multi-turn optimization, using live interaction, behavioral tests, and product criteria."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.21833v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.21833v1", "title": "GameXpert-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Chinese Academy of Sciences", "Tencent (China)", "Institute of Automation", "Tsinghua University", "Hong Kong University of Science and Technology", "Chinese University of Hong Kong, Shenzhen"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.21833", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.21833", "source_url": "https://openalex.org/W7204193705"}, "key": "claire-radar:2608.21833", "modality": null, "name": "GameXpert-Bench", "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": "true", "origin_record_id": "bm_gamexpert-bench_691da8d8", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "31f3a9dc020815c8b2daef1b16b864a4dd630b9830cd73ce3d607d262e2f04de", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-25T17:38:30.498900Z", "source_url": "https://arxiv.org/abs/2608.21833v1"}, "publisher": null, "released": "2026-08-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.21833", "source_url": "https://arxiv.org/abs/2608.21833v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-21833", "source": "claire_radar", "source_benchmark_id": "2608.21833", "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": 18, "hfPaperUrl": "https://huggingface.co/papers/2608.21833", "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": "2026-09-30", "state": "stale"}}, "status": "stale"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Game development is a novel and engaging application area for coding agents, though the benchmark's size and complexity may limit immediate adoption.", "score": 66}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T17:38:30.498900Z", "inputHash": "100349822a5c8bd9dce7418c55bf7b909c17fbdaa688d4be5e5a5bbdfe006aeb", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?", "canonicalNameSource": "paper_title", "decisionReason": "GameXpert-Bench is a formally named benchmark with three tracks and evaluation methods; the paper implies release of the suite for other teams.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T17:38:30.498900Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates coding agents across three game development lifecycle tracks: generation, bug diagnosis and repair, and multi-turn optimization, using live interaction, behavioral tests, and product criteria.", "displayEligible": true, "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": "Therefore, we introduce GameXpert-Bench, which operationalizes the three lifecycle stages as three complementary benchmark tracks."}, "familyId": "bmf_343bc4dacfb9", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_gamexpert-bench_691da8d8", "indexedAt": "2026-08-25T17:37:25.889905Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "http://arxiv.org/abs/2608.21833v1", "pdf": "https://arxiv.org/pdf/2608.21833v1", "project": null, "report": "http://arxiv.org/abs/2608.21833v1"}, "metrics": [], "motivation": "Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requests.", "name": "GameXpert-Bench", "oneLine": "Evaluates coding agents across three game development lifecycle tracks: generation, bug diagnosis and repair, and multi-turn optimization, using live interaction, behavioral tests, and product criteria.", "paperTitle": "GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.21833v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-25T17:37:25.889905Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.5202664955757326, "value": 18}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 50}, "method": "attention-ranking-v13", "rank": null, "score": 50}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-22", "source": {"authors": ["Kun Chen", "Haorong Hong", "Peizhong Gao", "Jianfeng Lin", "Tongxu Luo", "Yuxuan Xie", "Chenxu Liu", "Jieling He", "Zhongyuan Liu", "Zeno Zeng"], "categories": ["cs.AI", "cs.CL"], "id": "2608.21833", "title": "GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?", "type": "arxiv", "url": "http://arxiv.org/abs/2608.21833v1"}, "sourceUpdatedAt": "2026-08-22T08:05:16Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Provides a comprehensive benchmark for game development with coding agents, measuring both product quality and process capabilities across the full lifecycle."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
