{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.27141", "kind": "paper", "url": "https://arxiv.org/abs/2605.27141"}, {"id": "gh:meituan-longcat/vitabench-2.0", "kind": "repo", "url": "https://github.com/meituan-longcat/vitabench-2.0"}], "authors": ["Yuxin Chen", "Yi Zhang", "Zhengzhou Cai", "Yaorui Shi", "Zhiyuan Yao", "Chenhang Cui", "Jingnan Zheng", "Yaqi Huo", "Xi Su", "Qi Gu", "Xunliang Cai", "Xiang Wang", "An Zhang", "Tat-Seng Chua"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.27141", "source_url": "https://arxiv.org/abs/2605.27141"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "VitaBench 2.0 evaluates personalized and proactive agent behavior in long-term, multi-session user interactions across food delivery, in-store consumption, and online travel domains. Tasks are per-user sequences of subtasks requiring agents to infer, utilize, and update user preferences from fragmented interaction history, with an extensible memory interface for controlled comparison across memory architectures."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.27141", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.27141", "title": "VitaBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["National University of Singapore", "Meituan (China)", "University of Science and Technology of China", "Beijing University of Posts and Telecommunications", "Zhejiang University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.27141", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.27141", "source_url": "https://openalex.org/W7162484303"}, "key": "claire-radar:2605.27141", "modality": null, "name": "VitaBench", "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_vitabench_d7ecb50f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ae25c9b5703dc80c9d6c8c354666a2c723ba86cd4d73c1ce6b7e109365527f7a", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.27141"}, "publisher": null, "released": "2026-05-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.27141", "source_url": "https://arxiv.org/abs/2605.27141"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-27141", "source": "claire_radar", "source_benchmark_id": "2605.27141", "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": "https://github.com/meituan-longcat/vitabench-2.0", "githubScope": "benchmark_repo", "githubStars": 70, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 17, "hfPaperUrl": "https://huggingface.co/papers/2605.27141", "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": [], "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": "9f68e150f3c43b78ef0ca220cd8ebd80f69ec08e04ed58d8987ee39ec55825b5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VitaBench 2.0 evaluates personalized and proactive agent behavior in long-term, multi-session user interactions across food delivery, in-store consumption, and online travel domains. Tasks are per-user sequences of subtasks requiring agents to infer, utilize, and update user preferences from fragmented interaction history, with an extensible memory interface for controlled comparison across memory architectures.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this gap, we introduce VitaBench 2.0, a benchmark for evaluating personalized and proactive agent behavior in long-term user interactions."}, "familyId": "bmf_2e1c2e7b149d", "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/meituan-longcat/vitabench-2.0", "url": "https://github.com/meituan-longcat/vitabench-2.0"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/meituan-longcat/vitabench-2.0", "url": "https://huggingface.co/papers/2605.27141"}], "scope": "benchmark_repo", "url": "https://github.com/meituan-longcat/vitabench-2.0", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_vitabench_d7ecb50f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/meituan-longcat/vitabench-2.0", "data": null, "hfPaper": "https://huggingface.co/papers/2605.27141", "paper": "https://arxiv.org/abs/2605.27141", "pdf": "https://arxiv.org/pdf/2605.27141", "project": null, "report": "https://arxiv.org/abs/2605.27141"}, "metrics": [], "motivation": "Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks.", "name": "VitaBench", "oneLine": "VitaBench 2.0 evaluates personalized and proactive agent behavior in long-term, multi-session user interactions across food delivery, in-store consumption, and online travel domains. Tasks are per-user sequences of subtasks requiring agents to infer, utilize, and update user preferences from fragmented interaction history, with an extensible memory interface for controlled comparison across memory architectures.", "paperTitle": "VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.27141", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Meituan", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/meituan-longcat/vitabench-2.0"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-26", "source": {"authors": ["Yuxin Chen", "Yi Zhang", "Zhengzhou Cai", "Yaorui Shi", "Zhiyuan Yao", "Chenhang Cui", "Jingnan Zheng", "Yaqi Huo", "Xi Su", "Qi Gu", "Xunliang Cai", "Xiang Wang", "An Zhang", "Tat-Seng Chua"], "categories": ["cs.AI"], "id": "2605.27141", "title": "VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions", "type": "arxiv", "url": "https://arxiv.org/abs/2605.27141"}, "sourceUpdatedAt": "2026-05-26T15:07:38Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Existing agent benchmarks focus on reasoning and tool use, overlooking the challenges of inferring and leveraging user preferences over time. This benchmark isolates personalization and proactivity in long-horizon tasks, providing a measurement of practical readiness for life-serving applications where models must act on implicit and evolving user needs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
