{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.22366", "kind": "paper", "url": "https://arxiv.org/abs/2605.22366"}, {"id": "hf:agrotools/agrotools", "kind": "dataset", "url": "https://huggingface.co/datasets/AgroTools/AgroTools"}], "authors": ["Zi Ye", "Yibin Wen", "Xiaoya Fan", "Xinyu Zhang", "Jing Wu", "Kun Zeng", "Zurong Mai", "Jiarui Zhang", "Bohan Shi", "Juepeng Zheng", "Jianxi Huang", "Yutong Lu", "Haohuan Fu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.22366", "source_url": "https://arxiv.org/abs/2605.22366"}, "categories": ["General AI", "Multimodal"], "description": {"en": "AgroTools evaluates tool-augmented multimodal agents in agriculture, with 539 QA instances, 1,097 images, 14 executable tools, and structured tool-use traces for process and outcome evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.22366", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.22366", "title": "AgroTools"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.22366", "modality": null, "name": "AgroTools", "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_agrotools_ca69be78", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "727da87946b2b8989cbb8e05c3677f0cee958033845ecc6dbde56a80ba20d47d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.22366"}, "publisher": null, "released": "2026-05-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.22366", "source_url": "https://arxiv.org/abs/2605.22366"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-22366", "source": "claire_radar", "source_benchmark_id": "2605.22366", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": "AgroTools/AgroTools", "hfDatasetDownloads": 87, "hfDatasetLikes": 2, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2605.22366", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "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": "3a593c4aa01e277c30178213cb4c9e9f303445f60b0cf9175cd4500fd396d304", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AgroTools evaluates tool-augmented multimodal agents in agriculture, with 539 QA instances, 1,097 images, 14 executable tools, and structured tool-use traces for process and outcome evaluation.", "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": "In this paper, we introduce AgroTools, a benchmark for evaluating tool-augmented multimodal agents in agriculture."}, "familyId": "bmf_c721caf5d4ed", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "candidates"}, "heat": null, "id": "bm_agrotools_ca69be78", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": "https://huggingface.co/datasets/AgroTools/AgroTools", "hfPaper": "https://huggingface.co/papers/2605.22366", "paper": "https://arxiv.org/abs/2605.22366", "pdf": "https://arxiv.org/pdf/2605.22366", "project": null, "report": "https://arxiv.org/abs/2605.22366"}, "metrics": [], "motivation": "Agricultural decision-making increasingly requires multimodal systems that can transform visual observations into reliable, executable actions.", "name": "AgroTools", "oneLine": "AgroTools evaluates tool-augmented multimodal agents in agriculture, with 539 QA instances, 1,097 images, 14 executable tools, and structured tool-use traces for process and outcome evaluation.", "paperTitle": "AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in Agriculture", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.22366", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-21", "source": {"authors": ["Zi Ye", "Yibin Wen", "Xiaoya Fan", "Xinyu Zhang", "Jing Wu", "Kun Zeng", "Zurong Mai", "Jiarui Zhang", "Bohan Shi", "Juepeng Zheng", "Jianxi Huang", "Yutong Lu", "Haohuan Fu"], "categories": ["cs.CV"], "id": "2605.22366", "title": "AgroTools: A Benchmark for Tool-Augmented Multimodal Agents in Agriculture", "type": "arxiv", "url": "https://arxiv.org/abs/2605.22366"}, "sourceUpdatedAt": "2026-05-21T11:58:54Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Fills a gap in agricultural benchmarks by assessing tool use and workflow execution, not just final answers, enabling deeper evaluation of agent capabilities."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
