{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.15127", "kind": "paper", "url": "https://arxiv.org/abs/2608.15127"}], "categories": ["General AI", "Language & Knowledge", "cs.OS"], "description": {"en": "AgentSysBench is a benchmark suite and measurement toolkit for characterizing agentic workloads on LLM serving systems. It includes ten representative agentic applications and unified instrumentation, identifying six properties that distinguish agentic workloads from conventional LLM inference."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.15127", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.15127", "title": "AgentSysBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.15127", "modality": null, "name": "AgentSysBench", "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_agentsysbench_213ca6e5", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f8bb098d2e036cc99b5b5018cb39a54938e05acc3724b8ac29d4be78d1fd5011", "relation": "aggregates", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.15127"}, "publisher": null, "released": "2026-08-15", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.15127", "source_url": "https://arxiv.org/abs/2608.15127"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-15127", "source": "claire_radar", "source_benchmark_id": "2608.15127", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2608.15127", "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": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "669ded87be577731c12b75ef463ae18277f70618c04fa3be18502ca2e58a8632", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AgentSysBench is a benchmark suite and measurement toolkit for characterizing agentic workloads on LLM serving systems. It includes ten representative agentic applications and unified instrumentation, identifying six properties that distinguish agentic workloads from conventional LLM inference.", "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": "We present AgentSysBench, a benchmark suite and measurement toolkit with ten representative agentic applications and unified systems-level instrumentation."}, "familyId": "bmf_ff8fb088901b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_agentsysbench_213ca6e5", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.15127", "paper": "https://arxiv.org/abs/2608.15127", "pdf": "https://arxiv.org/pdf/2608.15127", "project": null, "report": "https://arxiv.org/abs/2608.15127"}, "metrics": [], "motivation": "Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state.", "name": "AgentSysBench", "oneLine": "AgentSysBench is a benchmark suite and measurement toolkit for characterizing agentic workloads on LLM serving systems. It includes ten representative agentic applications and unified instrumentation, identifying six properties that distinguish agentic workloads from conventional LLM inference.", "paperTitle": "From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.15127", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "aggregates", "releasedAt": "2026-08-15", "source": {"authors": ["Chaokun Chang", "Yukun Zhou", "Kaihua Fu", "Dakai An", "Tianyu Feng", "Hanfeng Lu", "Sheng Yao", "Pu Guo", "Yinghao Yu", "Yizhou Shan", "Bo Li", "Binhang Yuan", "Wei Wang"], "categories": ["cs.OS", "cs.AI", "cs.DC", "cs.MA"], "id": "2608.15127", "title": "From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems", "type": "arxiv", "url": "https://arxiv.org/abs/2608.15127"}, "sourceUpdatedAt": "2026-08-15T09:02:16Z", "topics": ["cs.OS"], "venueAttempts": [], "whyItMatters": "Serving systems are designed for conventional LLM inference and may not handle agentic workloads efficiently. AgentSysBench provides a measurement-based characterization that could guide system design for agentic applications."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
