{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2610.04379", "kind": "paper", "url": "https://arxiv.org/abs/2610.04379"}], "authors": ["Jintao Huang", "Yifan Wang", "Hongyu Shen", "Yi Daniel Lu", "Shirley Huang", "Minsik Oh", "Yewen Wang", "Muhammad Ahmed Mohsin", "Zhen Xu", "Yilan Fan", "Zichen Yuan", "Ahsan Bilal", "Zibu Wei", "Sankalp Jajee", "Henry Gagnier", "Saksham Kapoor", "Jicheng Wang", "Qianfeng Wen", "Yixuan He", "Steven Dillmann", "Jiashu He", "Yucheng Lu", "Linqiang Guo", "Danyang Zhang", "Shi Bo", "Raunak Mondal", "Haixiang Tang", "Weihang Xiao", "Allen Nie", "Jing Tang", "Yueying Li", "Yifan Simon Liu", "Jianheng Hou", "Dianzhuo Wang", "Qianyu Zhu", "Zhixu Silvia Tao", "Zhejian Peng", "Zihan Wang", "Ishan Gupta", "Jinxuan Fan", "Wanting Jiang", "Shushu Liang", "Chenxi Qiu", "Yijun Wang", "Xiaomin Li", "Yuexing Hao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2610.04379", "source_url": "https://arxiv.org/abs/2610.04379"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "We introduce AgentPersonaBench (APB), a benchmark evaluating whether persona conditioning faithfully steers downstream agent behavior."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2610.04379", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2610.04379", "title": "AgentPersonaBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2610.04379", "modality": null, "name": "AgentPersonaBench", "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_agentpersonabench_cb57cfe4", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1c4561e9efba32c41b8228dbd873f99596bbb04f1770cf55700ea425c4e94987", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-10-06T07:49:35.626614Z", "source_url": "https://arxiv.org/abs/2610.04379"}, "publisher": null, "released": "2026-10-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2610.04379", "source_url": "https://arxiv.org/abs/2610.04379"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2610-04379", "source": "claire_radar", "source_benchmark_id": "2610.04379", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "capabilities": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-10-06T07:49:35.626614Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "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": "We introduce AgentPersonaBench (APB), a benchmark evaluating whether persona conditioning faithfully steers downstream agent behavior."}, "familyId": "bmf_aeaaf9608e09", "firstSeenAt": "2026-10-06", "heat": null, "id": "bm_agentpersonabench_cb57cfe4", "indexedAt": "2026-10-06T07:49:11.852971Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2610.04379", "pdf": "https://arxiv.org/pdf/2610.04379", "project": null, "report": "https://arxiv.org/abs/2610.04379"}, "metrics": [], "motivation": "We introduce AgentPersonaBench (APB), a benchmark evaluating whether persona conditioning faithfully steers downstream agent behavior.", "name": "AgentPersonaBench", "oneLine": "We introduce AgentPersonaBench (APB), a benchmark evaluating whether persona conditioning faithfully steers downstream agent behavior.", "paperTitle": "AgentPersonaBench: Benchmarking Persona-Driven User Simulation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2610.04379", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-10-03", "source": {"authors": ["Jintao Huang", "Yifan Wang", "Hongyu Shen", "Yi Daniel Lu", "Shirley Huang", "Minsik Oh", "Yewen Wang", "Muhammad Ahmed Mohsin", "Zhen Xu", "Yilan Fan", "Zichen Yuan", "Ahsan Bilal", "Zibu Wei", "Sankalp Jajee", "Henry Gagnier", "Saksham Kapoor", "Jicheng Wang", "Qianfeng Wen", "Yixuan He", "Steven Dillmann", "Jiashu He", "Yucheng Lu", "Linqiang Guo", "Danyang Zhang", "Shi Bo", "Raunak Mondal", "Haixiang Tang", "Weihang Xiao", "Allen Nie", "Jing Tang", "Yueying Li", "Yifan Simon Liu", "Jianheng Hou", "Dianzhuo Wang", "Qianyu Zhu", "Zhixu Silvia Tao", "Zhejian Peng", "Zihan Wang", "Ishan Gupta", "Jinxuan Fan", "Wanting Jiang", "Shushu Liang", "Chenxi Qiu", "Yijun Wang", "Xiaomin Li", "Yuexing Hao"], "categories": ["cs.AI"], "id": "2610.04379", "title": "AgentPersonaBench: Benchmarking Persona-Driven User Simulation", "type": "arxiv", "url": "https://arxiv.org/abs/2610.04379"}, "sourceUpdatedAt": "2026-10-03T08:45:45Z", "topics": ["Agents"], "venueAttempts": []}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
