{"record": {"aliases": ["WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing"], "artifacts": [{"id": "arxiv:2609.05171", "kind": "paper", "url": "https://arxiv.org/abs/2609.05171"}], "authors": ["Hui Zhang", "Zongkai Liu", "Liqiang Niu", "Juntao Liu", "Han Li", "Zhen Cao", "Wenchao Chen", "Chengduo Zhao", "Fandong Meng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.05171", "source_url": "https://arxiv.org/abs/2609.05171"}, "categories": ["Agents", "General AI", "Multimodal"], "description": {"en": "Evaluates multimodal agentic image generation and editing, focusing on knowledge-intensive generation and multi-image editing across bilingual prompts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.05171", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.05171", "title": "WeBench-MMGenEdit"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.05171", "modality": null, "name": "WeBench-MMGenEdit", "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_weagent-mmgenedit-a-full-stack-recipe-for-_1dc7d757", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "c3ec6cb16c53a44682757df65fc780668405f4888d6edea5cc98219b4c5cb368", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-09T09:03:45.514878Z", "source_url": "https://arxiv.org/abs/2609.05171"}, "publisher": null, "released": "2026-09-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.05171", "source_url": "https://arxiv.org/abs/2609.05171"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-05171", "source": "claire_radar", "source_benchmark_id": "2609.05171", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing"], "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": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2609.05171", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses a specialized multimodal agentic task with a full-stack recipe, likely attracting moderate attention in the image generation and editing community.", "score": 65}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T09:03:45.514878Z", "inputHash": "dec8579335c4597fbd5ec3ed6c6a4a971182b259a477aadbf7ec6fb36805926e", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "We further introduce WeBench-MMGenEdit, a bilingual benchmark covering both knowledge-intensive image generation and multi-image editing.", "canonicalNameSource": "abstract", "decisionReason": "A formally named benchmark with defined tasks, scoring via verifiable checklists, and a public reuse path via the scalable data construction pipeline.", "evaluationEvidence": {"reuse": "Benchmark introduced as part of a full-stack recipe with a scalable data construction pipeline.", "scoring": "Three-layer verifiable checklists in 14.7K RL tasks.", "task": "Bilingual benchmark covering knowledge-intensive image generation and multi-image editing."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-09T09:03:45.514878Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multimodal agentic image generation and editing, focusing on knowledge-intensive generation and multi-image editing across bilingual prompts.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address these limitations, we present WeAgent-MMGenEdit, a full-stack recipe including a multimodal harness, a scalable data construction pipeline, a comprehensive benchmark, and post-training methods for the agent policy and image backend."}, "familyId": "bmf_3562a9d533b4", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_weagent-mmgenedit-a-full-stack-recipe-for-_1dc7d757", "indexedAt": "2026-09-07T06:22:02.605340Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.05171", "pdf": "https://arxiv.org/pdf/2609.05171", "project": null, "report": "https://arxiv.org/abs/2609.05171"}, "metrics": [], "motivation": "Image generation and editing models have advanced rapidly, yet remain unreliable when prompts require external world knowledge.", "name": "WeBench-MMGenEdit", "oneLine": "Evaluates multimodal agentic image generation and editing, focusing on knowledge-intensive generation and multi-image editing across bilingual prompts.", "paperTitle": "WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.05171", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T06:22:02.605340Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-09-04", "source": {"authors": ["Hui Zhang", "Zongkai Liu", "Liqiang Niu", "Juntao Liu", "Han Li", "Zhen Cao", "Wenchao Chen", "Chengduo Zhao", "Fandong Meng"], "categories": ["cs.CV"], "id": "2609.05171", "title": "WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing", "type": "arxiv", "url": "https://arxiv.org/abs/2609.05171"}, "sourceUpdatedAt": "2026-09-04T14:12:03Z", "topics": ["Agents", "Multimodal"], "venueAttempts": [], "whyItMatters": "Addresses the gap in reliable image generation and editing that requires external world knowledge, with integrated visual verification."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
