{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.04874", "kind": "paper", "url": "https://arxiv.org/abs/2606.04874"}, {"id": "gh:mikivishy/agentplanningbenchmark", "kind": "repo", "url": "https://github.com/Mikivishy/AgentPlanningBenchmark"}], "authors": ["Haoyu Sun", "Wenxuan Wang", "Mingyang Song", "Jujie He", "Weinan Zhang", "Yang Liu", "Yang Yang", "Yu Cheng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.04874", "source_url": "https://arxiv.org/abs/2606.04874"}, "categories": ["Agents", "General AI", "Multimodal", "Planning", "Robustness", "Safety & Trustworthiness"], "description": {"en": "Agent Planning Benchmark (APB) is a diagnostic benchmark with 4,209 multimodal cases across 22 domains, evaluating planning capabilities in five settings including tool noise and unsolvable tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.04874", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.04874", "title": "Agent Planning Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.04874", "modality": null, "name": "Agent Planning Benchmark", "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_agent-planning-benchmark_ba86aa47", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e622a4f5c690ce5387ced8b3a66c41eb1ad04547dc5764446484dd97759c5d50", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.04874"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.04874", "source_url": "https://arxiv.org/abs/2606.04874"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-04874", "source": "claire_radar", "source_benchmark_id": "2606.04874", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Safety & Trustworthiness", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Mikivishy/AgentPlanningBenchmark", "githubScope": "benchmark_repo", "githubStars": 6, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.04874", "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": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Planning", "Robustness"], "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": "ce2467c3e2d3a7e58a80d61c03d04197e43368639a0b6597576cb2b69aea1082", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Agent Planning Benchmark (APB) is a diagnostic benchmark with 4,209 multimodal cases across 22 domains, evaluating planning capabilities in five settings including tool noise and unsolvable tasks.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce Agent Planning Benchmark (APB), a planning-specific diagnostic benchmark with 4,209 multimodal cases across 22 domains and five settings, covering holistic planning, feedback-conditioned step-wise planning, and robustness under extraneous tools, broken tools, and unsolvable tasks."}, "familyId": "bmf_13413c2da00d", "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/Mikivishy/AgentPlanningBenchmark", "url": "https://github.com/Mikivishy/AgentPlanningBenchmark"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Mikivishy/AgentPlanningBenchmark", "url": "https://huggingface.co/papers/2606.04874"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Mikivishy/AgentPlanningBenchmark", "url": "https://arxiv.org/abs/2606.04874"}], "scope": "benchmark_repo", "url": "https://github.com/Mikivishy/AgentPlanningBenchmark", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_agent-planning-benchmark_ba86aa47", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Mikivishy/AgentPlanningBenchmark", "data": null, "hfPaper": "https://huggingface.co/papers/2606.04874", "paper": "https://arxiv.org/abs/2606.04874", "pdf": "https://arxiv.org/pdf/2606.04874", "project": null, "report": "https://arxiv.org/abs/2606.04874"}, "metrics": [], "motivation": "Planning is central to LLM agents: before acting, an agent must decompose goals, select tools, reason over constraints, and decide when a task is infeasible.", "name": "Agent Planning Benchmark", "oneLine": "Agent Planning Benchmark (APB) is a diagnostic benchmark with 4,209 multimodal cases across 22 domains, evaluating planning capabilities in five settings including tool noise and unsolvable tasks.", "paperTitle": "Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.04874", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "APB Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Mikivishy/AgentPlanningBenchmark"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Haoyu Sun", "Wenxuan Wang", "Mingyang Song", "Jujie He", "Weinan Zhang", "Yang Liu", "Yang Yang", "Yu Cheng"], "categories": ["cs.CL"], "id": "2606.04874", "title": "Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2606.04874"}, "sourceUpdatedAt": "2026-06-05T05:23:52Z", "topics": ["Agents", "Multimodal"], "venueAttempts": [], "whyItMatters": "Provides a planning-specific evaluation that isolates failures from execution, enabling targeted improvement of agent planning and refusal behaviors."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
