{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.27995", "kind": "paper", "url": "https://arxiv.org/abs/2605.27995"}, {"id": "gh:stokou/repo-asynctool", "kind": "repo", "url": "https://github.com/StoKou/repo-asynctool"}], "authors": ["Kou Shi", "Ziao Zhang", "Shiting Huang", "Avery Nie", "Zhen Fang", "Qiuchen Wang", "Lin Chen", "Huaian Chen", "Zehui Chen", "Feng Zhao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.27995", "source_url": "https://arxiv.org/abs/2605.27995"}, "categories": ["Agents & Tool Use", "General AI", "cs.AI"], "description": {"en": "AsyncTool is a benchmark for evaluating asynchronous function calling in multi-task tool-use environments. It presents multiple tasks with simulated tool response latency, assessing step-level tool-call correctness, sub-task completion, and task-level end-to-end success, along with efficiency-oriented metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.27995", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.27995", "title": "AsyncTool"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.27995", "modality": null, "name": "AsyncTool", "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_asynctool_407c214b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6cc628895d63f30e0534ffc8e33b429ee586c3472c3273a196b9ec2ab6e6b4f8", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.27995"}, "publisher": null, "released": "2026-05-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.27995", "source_url": "https://arxiv.org/abs/2605.27995"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-27995", "source": "claire_radar", "source_benchmark_id": "2605.27995", "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": "https://github.com/StoKou/repo-asynctool", "githubScope": "benchmark_repo", "githubStars": 102, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 11, "hfPaperUrl": "https://huggingface.co/papers/2605.27995", "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": "95896a723774ae6cbdf64037db9c11076b9462fd539755d0e5c13089ecf1e6f0", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AsyncTool is a benchmark for evaluating asynchronous function calling in multi-task tool-use environments. It presents multiple tasks with simulated tool response latency, assessing step-level tool-call correctness, sub-task completion, and task-level end-to-end success, along with efficiency-oriented metrics.", "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", "public artifact URL"], "snippet": "To evaluate it, we propose AsyncTool, a benchmark for assessing LLM-based agents in interactive multi-task tool-use environments with delayed tool feedback."}, "familyId": "bmf_ec6315a36e48", "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/StoKou/repo-asynctool", "url": "https://github.com/StoKou/repo-asynctool"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/StoKou/repo-asynctool", "url": "https://huggingface.co/papers/2605.27995"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/StoKou/repo-asynctool", "url": "https://huggingface.co/api/papers/2605.27995"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/StoKou/repo-asynctool", "url": "https://arxiv.org/abs/2605.27995"}], "scope": "benchmark_repo", "url": "https://github.com/StoKou/repo-asynctool", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_asynctool_407c214b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/StoKou/repo-asynctool", "data": null, "hfPaper": "https://huggingface.co/papers/2605.27995", "paper": "https://arxiv.org/abs/2605.27995", "pdf": "https://arxiv.org/pdf/2605.27995", "project": null, "report": "https://arxiv.org/abs/2605.27995"}, "metrics": [], "motivation": "Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks.", "name": "AsyncTool", "oneLine": "AsyncTool is a benchmark for evaluating asynchronous function calling in multi-task tool-use environments. It presents multiple tasks with simulated tool response latency, assessing step-level tool-call correctness, sub-task completion, and task-level end-to-end success, along with efficiency-oriented metrics.", "paperTitle": "AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.27995", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "AsyncTool Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/StoKou/repo-asynctool"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-27", "source": {"authors": ["Kou Shi", "Ziao Zhang", "Shiting Huang", "Avery Nie", "Zhen Fang", "Qiuchen Wang", "Lin Chen", "Huaian Chen", "Zehui Chen", "Feng Zhao"], "categories": ["cs.AI"], "id": "2605.27995", "title": "AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios", "type": "arxiv", "url": "https://arxiv.org/abs/2605.27995"}, "sourceUpdatedAt": "2026-05-28T05:56:15Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Real-world tool use involves delays, but existing benchmarks assume immediate responses. AsyncTool measures whether agents can coordinate multiple tasks and use idle time efficiently, identifying key failure modes for temporal reasoning and task coordination."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
