{"record": {"aliases": ["Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents"], "artifacts": [{"id": "arxiv:2609.11318", "kind": "paper", "url": "https://arxiv.org/abs/2609.11318"}, {"id": "gh:minghaoguo20/mr-lhdr-eval", "kind": "repo", "url": "https://github.com/minghaoguo20/Mr-LHDR-eval"}], "authors": ["Minghao Guo", "Meng Cao", "Sui Zhao", "Siyu Ning", "Xin Wang", "Haoze Zhao", "Jiaxuan Yang", "Haihong Hao", "Mingfei Han", "Shunlin Rong", "Haijun Wu", "Xiaodan Liang", "Xiaojun Chang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.11318", "source_url": "https://arxiv.org/abs/2609.11318"}, "categories": ["General AI", "Multimodal"], "description": {"en": "Benchmark of 102 research questions with explicit dependency graphs and step checklists for long-horizon multimodal deep research agents."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.11318", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.11318", "title": "Mr.LHDR"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.11318", "modality": null, "name": "Mr.LHDR", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "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_mr-lhdr-a-benchmark-for-multimodal-real-wo_b8dc47d7", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "9b4afe31437999f8546f6091a160f5e7b1f5ba985f29fbcb4986b218810e8581", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-14T00:43:53.625753Z", "source_url": "https://arxiv.org/abs/2609.11318"}, "publisher": null, "released": "2026-09-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.11318", "source_url": "https://arxiv.org/abs/2609.11318"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-11318", "source": "claire_radar", "source_benchmark_id": "2609.11318", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-09-11", "attemptedAt": "2026-09-11T01:40:00.759237Z", "githubRepo": "https://github.com/minghaoguo20/Mr-LHDR-eval", "githubScope": "benchmark_repo", "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.11318", "observedAt": "2026-09-10T12:24:43.080049Z", "signalStatus": {"githubStars": {"checkedAt": "2026-09-11T01:40:00.759237Z", "state": "unavailable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-11T01:40:00.759237Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Multimodal long-horizon agent evaluation is a hot topic, and the provided code and dataset are likely to draw early interest.", "score": 60}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-14T00:43:53.625753Z", "inputHash": "35745ad491f52f0e98b1b64d1fcf368c337398917e1cd8d9d28220ab1f4acac1", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents", "canonicalNameSource": "paper_title", "decisionReason": "Public repository with full evaluation pipeline; includes results for 25 systems and ongoing comparison path.", "evaluationEvidence": {"reuse": "GitHub repository with scripts for data download, decryption, running models, judging, and scoring; public code path.", "scoring": "Four metrics per item: OA, SA, CS, DACS, computed per item and averaged; LLM judge used for answer verification.", "task": "102 real-world research questions across eight categories, each with irreducible checklist of intermediate conclusions and dependency graph."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-14T00:43:53.625753Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Benchmark of 102 research questions with explicit dependency graphs and step checklists for long-horizon multimodal deep research agents.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We introduce Mr.LHDR (Multimodal real-world Long-Horizon Deep Research), a benchmark for evaluating real-world deep research over long, irreducible chains of interdependent evidence across eight categories."}, "familyId": "bmf_81e78b095bab", "firstSeenAt": "2026-09-11", "heat": null, "id": "bm_mr-lhdr-a-benchmark-for-multimodal-real-wo_b8dc47d7", "indexedAt": "2026-09-11T00:48:15.671466Z", "industrySectors": [], "links": {"code": "https://github.com/minghaoguo20/Mr-LHDR-eval", "data": null, "paper": "https://arxiv.org/abs/2609.11318", "pdf": "https://arxiv.org/pdf/2609.11318", "project": null, "report": "https://arxiv.org/abs/2609.11318"}, "metrics": [], "motivation": "Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis.", "name": "Mr.LHDR", "oneLine": "Benchmark of 102 research questions with explicit dependency graphs and step checklists for long-horizon multimodal deep research agents.", "paperTitle": "Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.11318", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-11T00:48:15.671466Z"}, "publications": [], "publishers": [{"name": "Minghao Guo's team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/minghaoguo20/Mr-LHDR-eval"}], "ranking": {"30d": {"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": 30}, "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}, "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}, "today": {"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": 1, "historyDate": "2026-09-10", "rank": null, "score": null, "windowDays": 1}, "level": {"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}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.75, "role": "bonus", "value": 75}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 19}, "method": "attention-ranking-v13", "rank": null, "score": 19}}, "readiness": "Runnable", "recognitionConfidence": 0.55, "relation": "introduces", "releasedAt": "2026-09-10", "source": {"authors": ["Minghao Guo", "Meng Cao", "Sui Zhao", "Siyu Ning", "Xin Wang", "Haoze Zhao", "Jiaxuan Yang", "Haihong Hao", "Mingfei Han", "Shunlin Rong", "Haijun Wu", "Xiaodan Liang", "Xiaojun Chang"], "categories": ["cs.AI"], "id": "2609.11318", "title": "Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2609.11318"}, "sourceUpdatedAt": "2026-09-10T09:47:44Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Enables fine-grained evaluation of agent reasoning with partial credit for dependency-consistent progress."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
