{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.29653", "kind": "paper", "url": "https://arxiv.org/abs/2605.29653"}], "authors": ["Dongdong Hua", "Yifei Sun", "Renhong Huang", "Feng Gao", "Chunping Wang", "Yang Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.29653", "source_url": "https://arxiv.org/abs/2605.29653"}, "categories": ["Agents & Tool Use", "General AI", "cs.AI"], "description": {"en": "PTCG-Bench evaluates LLM agents on the Pokémon Trading Card Game at two levels: single-environment decision-making and self-evolution through accumulated experience, with modular harness ablation to separate agent performance from harness design."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.29653", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.29653", "title": "PTCG-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.29653", "modality": null, "name": "PTCG-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_ptcg-bench_083265f8", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "1cc5b2101fbfd5aa11272a4a826bce5cd805eedec53d54f65785ddc0aba986a5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.29653"}, "publisher": null, "released": "2026-05-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.29653", "source_url": "https://arxiv.org/abs/2605.29653"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-29653", "source": "claire_radar", "source_benchmark_id": "2605.29653", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2605.29653", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "9afca48c8eef6595edba7a7df5ce6d7d1f2ceddc2975d3bd7b7ee73adbb2d453", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PTCG-Bench evaluates LLM agents on the Pokémon Trading Card Game at two levels: single-environment decision-making and self-evolution through accumulated experience, with modular harness ablation to separate agent performance from harness design.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We present PTCG-Bench, a benchmark built on the Pok'{e}mon Trading Card Game (PTCG) that evaluates LLM agents at two complementary levels: (1) their decision-making performance within a single complex environment, and (2) their ability to self-evolving through accumulated experience."}, "familyId": "bmf_dc9b6ac4f245", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_ptcg-bench_083265f8", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.29653", "paper": "https://arxiv.org/abs/2605.29653", "pdf": "https://arxiv.org/pdf/2605.29653", "project": null, "report": "https://arxiv.org/abs/2605.29653"}, "metrics": [], "motivation": "Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds.", "name": "PTCG-Bench", "oneLine": "PTCG-Bench evaluates LLM agents on the Pokémon Trading Card Game at two levels: single-environment decision-making and self-evolution through accumulated experience, with modular harness ablation to separate agent performance from harness design.", "paperTitle": "PTCG-Bench: Can LLM Agents Master Pok\\'emon Trading Card Game?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.29653", "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": "2026-05-28", "source": {"authors": ["Dongdong Hua", "Yifei Sun", "Renhong Huang", "Feng Gao", "Chunping Wang", "Yang Yang"], "categories": ["cs.AI"], "id": "2605.29653", "title": "PTCG-Bench: Can LLM Agents Master Pok\\'emon Trading Card Game?", "type": "arxiv", "url": "https://arxiv.org/abs/2605.29653"}, "sourceUpdatedAt": "2026-05-28T09:16:22Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Agent benchmarks often miss strategic and evolving decision-making. PTCG-Bench provides a realistic interactive environment to assess self-evolution and harness sensitivity, which are critical for deploying autonomous agents."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
