{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.29445", "kind": "paper", "url": "https://arxiv.org/abs/2606.29445"}, {"id": "gh:vg-gui-tasker/vg-gui-tasker", "kind": "repo", "url": "https://github.com/VG-GUI-TASKER/VG-GUI-TASKER"}, {"kind": "website", "url": "https://vg-gui-tasker.github.io/"}], "authors": ["Sunqi Fan", "Qingle Liu", "Runqi Yin", "Meng-Hao Guo", "Shuojin Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.29445", "source_url": "https://arxiv.org/abs/2606.29445"}, "categories": ["Agents & Tool Use", "General AI", "cs.CV"], "description": {"en": "VG-GUI-Bench evaluates MLLM-based GUI agents on following video tutorials to complete interactive tasks, with 1,000 long-horizon test cases and four metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.29445", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.29445", "title": "VG-GUIBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.29445", "modality": null, "name": "VG-GUIBench", "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_vg-guibench_23eefff5", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5ca3adf1d2274fd8d9368af753ede03e4ff94582f9b6e34b872688ea3efba96f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.29445"}, "publisher": null, "released": "2026-06-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.29445", "source_url": "https://arxiv.org/abs/2606.29445"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-29445", "source": "claire_radar", "source_benchmark_id": "2606.29445", "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/VG-GUI-TASKER/VG-GUI-TASKER", "githubScope": "benchmark_repo", "githubStars": 20, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 25, "hfPaperUrl": "https://huggingface.co/papers/2606.29445", "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": "2026-10-04", "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": "64a241c8ce1d20bf21e270316b808a1e681e5fe8998252866a35ceb5d8da392d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VG-GUI-Bench evaluates MLLM-based GUI agents on following video tutorials to complete interactive tasks, with 1,000 long-horizon test cases and four metrics.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce VG-GUIBench (Video-Guided GUI Benchmark), a new benchmark designed to evaluate whether MLLM-based GUI agents can follow video tutorials to complete corresponding GUI interactive tasks."}, "familyId": "bmf_42e90ac524ad", "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/VG-GUI-TASKER/VG-GUI-TASKER", "url": "https://github.com/VG-GUI-TASKER/VG-GUI-TASKER"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/VG-GUI-TASKER/VG-GUI-TASKER", "url": "https://huggingface.co/papers/2606.29445"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/VG-GUI-TASKER/VG-GUI-TASKER", "url": "https://vg-gui-tasker.github.io/"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/VG-GUI-TASKER/VG-GUI-TASKER.", "url": "https://arxiv.org/abs/2606.29445"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/VG-GUI-TASKER/VG-GUI-TASKER", "url": "https://arxiv.org/abs/2606.29445"}], "scope": "project_repo", "url": "https://github.com/VG-GUI-TASKER/VG-GUI-TASKER", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_vg-guibench_23eefff5", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/VG-GUI-TASKER/VG-GUI-TASKER", "data": null, "hfPaper": "https://huggingface.co/papers/2606.29445", "paper": "https://arxiv.org/abs/2606.29445", "pdf": "https://arxiv.org/pdf/2606.29445", "project": "https://vg-gui-tasker.github.io/", "report": "https://arxiv.org/abs/2606.29445"}, "metrics": [], "motivation": "Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Video Question Answering (VideoQA) benchmarks.", "name": "VG-GUIBench", "oneLine": "VG-GUI-Bench evaluates MLLM-based GUI agents on following video tutorials to complete interactive tasks, with 1,000 long-horizon test cases and four metrics.", "paperTitle": "Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction", "primaryDomain": "General AI", "publication": {"evidence": "Accepted by ECCV 2026. Project Page: https://vg-gui-tasker.github.io/", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.29445", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ECCV 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-28", "source": {"authors": ["Sunqi Fan", "Qingle Liu", "Runqi Yin", "Meng-Hao Guo", "Shuojin Yang"], "categories": ["cs.CV", "cs.AI"], "id": "2606.29445", "title": "Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction", "type": "arxiv", "url": "https://arxiv.org/abs/2606.29445"}, "sourceUpdatedAt": "2026-06-28T15:11:19Z", "topics": ["cs.CV"], "venueAttempts": [{"decisionRaw": "Accepted by ECCV 2026. Project Page: https://vg-gui-tasker.github.io/", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted by ECCV 2026. Project Page: https://vg-gui-tasker.github.io/", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.29445"}], "reviewStatus": "accepted", "venueName": "ECCV 2026"}], "whyItMatters": "The benchmark addresses video-guided agentic tasks, complementing VideoQA benchmarks for procedural knowledge transfer."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
