{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.24509", "kind": "paper", "url": "https://arxiv.org/abs/2608.24509"}, {"id": "gh:czzzk/staggering-the-peaks", "kind": "repo", "url": "https://github.com/Czzzk/Staggering-the-Peaks"}], "authors": ["Zhi-Kai Chen", "Xu-Xiang Zhong", "Song-Yan Li", "De-Chuan Zhan", "Han-Jia Ye"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.24509", "source_url": "https://arxiv.org/abs/2608.24509"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "PeakBench is a benchmark of executable multi-tool workflows for evaluating resource-aware tool invocation in LLM agents. It includes execution-grounded dependency annotations and measured resource profiles, with a two-part evaluation framework distinguishing logical planning from physical scheduling. Code is available on GitHub."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.24509", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.24509", "title": "PeakBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Nanjing University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.24509", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.24509", "source_url": "https://openalex.org/W7204260397"}, "key": "claire-radar:2608.24509", "modality": null, "name": "PeakBench", "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_peakbench_8142057d", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b6014b0ec290d9d7e09f10559da85c3314dbd173c1129fd9f82f6aa5d8910dc4", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:08:47.245811Z", "source_url": "https://arxiv.org/abs/2608.24509"}, "publisher": null, "released": "2026-08-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.24509", "source_url": "https://arxiv.org/abs/2608.24509"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-24509", "source": "claire_radar", "source_benchmark_id": "2608.24509", "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/Czzzk/Staggering-the-Peaks", "githubScope": "benchmark_repo", "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.24509", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Specialized topic in LLM agents; code availability may generate moderate interest among agent researchers.", "score": 55}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:22:25.189955Z", "inputHash": "60282cff8ca5502cfcd6f3e7177a1626619bb6e90e24a4b740c677419d3e3c09", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents", "canonicalNameSource": "paper_title", "decisionReason": "Code link is provided; the benchmark includes a defined two-part evaluation framework with dedicated metrics.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:08:47.245811Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PeakBench is a benchmark of executable multi-tool workflows for evaluating resource-aware tool invocation in LLM agents. It includes execution-grounded dependency annotations and measured resource profiles, with a two-part evaluation framework distinguishing logical planning from physical scheduling. Code is available on GitHub.", "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", "public artifact URL"], "snippet": "To address this gap, we introduce PeakBench, a benchmark of executable multi-tool workflows with execution-grounded dependency annotations and measured resource profiles."}, "familyId": "bmf_3fec537d2f24", "firstSeenAt": "2026-08-26", "heat": null, "id": "bm_peakbench_8142057d", "indexedAt": "2026-08-26T06:08:22.244942Z", "industrySectors": [], "links": {"code": "https://github.com/Czzzk/Staggering-the-Peaks", "data": null, "paper": "https://arxiv.org/abs/2608.24509", "pdf": "https://arxiv.org/pdf/2608.24509", "project": null, "report": "https://arxiv.org/abs/2608.24509"}, "metrics": [], "motivation": "LLM agents increasingly solve tasks by invoking multiple tools, where parallel execution is essential for low latency but difficult to manage safely.", "name": "PeakBench", "oneLine": "PeakBench is a benchmark of executable multi-tool workflows for evaluating resource-aware tool invocation in LLM agents. It includes execution-grounded dependency annotations and measured resource profiles, with a two-part evaluation framework distinguishing logical planning from physical scheduling. Code is available on GitHub.", "paperTitle": "PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.24509", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-26T06:08:22.244942Z"}, "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": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-25", "source": {"authors": ["Zhi-Kai Chen", "Xu-Xiang Zhong", "Song-Yan Li", "De-Chuan Zhan", "Han-Jia Ye"], "categories": ["cs.AI", "cs.SE"], "id": "2608.24509", "title": "PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2608.24509"}, "sourceUpdatedAt": "2026-08-25T12:56:08Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing agent benchmarks overlook parallelization and resource-constrained scheduling, creating practical failure modes. PeakBench provides a testbed to diagnose resource-aware agent behavior, helping improve safe and efficient tool execution."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
