Qwen3.7-Max/Plus is already live as a closed API — any plans for open-weight releases of the 3.7 family? (like 3.6-35B-A3B / 3.6-27B alongside 3.6-Max)</p>\n<p>Would love to run it locally via llama.cpp / GGUF.</p>\n","updatedAt":"2026-06-26T19:22:19.830Z","author":{"_id":"679223db89c82d08b2cd18c3","avatarUrl":"/avatars/e09e649f4a90014d18f6ee5436b5d2dc.svg","fullname":"xyz","name":"xyzblaz","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8949437141418457},"editors":["xyzblaz"],"editorAvatarUrls":["/avatars/e09e649f4a90014d18f6ee5436b5d2dc.svg"],"reactions":[{"reaction":"➕","users":["olborer"],"count":1}],"isReport":false}},{"id":"6a3f90daaf3243243b7b866a","author":{"_id":"6798524d208ffebef59bda01","avatarUrl":"/avatars/5d23dffe695bfd9046eced3d84d78c47.svg","fullname":"JiangchengWang","name":"JiangchengWang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2026-06-27T08:59:06.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"The current wording of Figure 1’s caption is not sufficiently precise. “Generated without providing visual references” could be read as “generated without using visual references,” which conflicts with the agentic design described in the paper. Since Qwen-Image-Agent is able to search for and incorporate external visual references, the caption should clarify that the absence refers to user-provided visual references, not to visual references acquired by the agent itself. A more accurate caption would be: “Qwen-Image-Agent examples generated without user-provided visual references.”","html":"<p>The current wording of Figure 1’s caption is not sufficiently precise. “Generated without providing visual references” could be read as “generated without using visual references,” which conflicts with the agentic design described in the paper. Since Qwen-Image-Agent is able to search for and incorporate external visual references, the caption should clarify that the absence refers to user-provided visual references, not to visual references acquired by the agent itself. A more accurate caption would be: “Qwen-Image-Agent examples generated without user-provided visual references.”</p>\n","updatedAt":"2026-06-27T08:59:06.920Z","author":{"_id":"6798524d208ffebef59bda01","avatarUrl":"/avatars/5d23dffe695bfd9046eced3d84d78c47.svg","fullname":"JiangchengWang","name":"JiangchengWang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8947555422782898},"editors":["JiangchengWang"],"editorAvatarUrls":["/avatars/5d23dffe695bfd9046eced3d84d78c47.svg"],"reactions":[{"reaction":"🤗","users":["JiangchengWang"],"count":1}],"isReport":false}},{"id":"6a3f96547a3e55a062e16262","author":{"_id":"65c867cf1b1a5743b3d2fc58","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65c867cf1b1a5743b3d2fc58/1c8vQtwY7ZNl4e4U4pAix.jpeg","fullname":"Yaochen Wang","name":"MisakiWang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false},"createdAt":"2026-06-27T09:22:28.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Hi team, thanks for the great work on Qwen-Image-Agent. I’m very interested in IA-Bench and the agentic generation pipeline.\nDo you plan to open-source the code and IA-Bench dataset/evaluation scripts? If yes, is there an estimated release timeline?\nThanks!","html":"<p>Hi team, thanks for the great work on Qwen-Image-Agent. I’m very interested in IA-Bench and the agentic generation pipeline.<br>Do you plan to open-source the code and IA-Bench dataset/evaluation scripts? If yes, is there an estimated release timeline?<br>Thanks!</p>\n","updatedAt":"2026-06-27T09:22:28.318Z","author":{"_id":"65c867cf1b1a5743b3d2fc58","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/65c867cf1b1a5743b3d2fc58/1c8vQtwY7ZNl4e4U4pAix.jpeg","fullname":"Yaochen Wang","name":"MisakiWang","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8674302101135254},"editors":["MisakiWang"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/65c867cf1b1a5743b3d2fc58/1c8vQtwY7ZNl4e4U4pAix.jpeg"],"reactions":[{"reaction":"🤗","users":["rain305"],"count":1}],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.26907","authors":[{"_id":"6a3ddcfb3b43e283349ec11d","name":"Zekai Zhang","hidden":false},{"_id":"6a3ddcfb3b43e283349ec11e","name":"Jiahao Li","hidden":false},{"_id":"6a3ddcfb3b43e283349ec11f","name":"Jie Zhang","hidden":false},{"_id":"6a3ddcfb3b43e283349ec120","name":"Kaiyuan Gao","hidden":false},{"_id":"6a3ddcfb3b43e283349ec121","name":"Kun Yan","hidden":false},{"_id":"6a3ddcfb3b43e283349ec122","name":"Lihan Jiang","hidden":false},{"_id":"6a3ddcfb3b43e283349ec123","name":"Ningyuan Tang","hidden":false},{"_id":"6a3ddcfb3b43e283349ec124","name":"Shengming Yin","hidden":false},{"_id":"6a3ddcfb3b43e283349ec125","name":"Tianhe Wu","hidden":false},{"_id":"6a3ddcfb3b43e283349ec126","name":"Xiaoyue Chen","hidden":false},{"_id":"6a3ddcfb3b43e283349ec127","name":"Xiao Xu","hidden":false},{"_id":"6a3ddcfb3b43e283349ec128","name":"Yan Shu","hidden":false},{"_id":"6a3ddcfb3b43e283349ec129","name":"Yanran Zhang","hidden":false},{"_id":"6a3ddcfb3b43e283349ec12a","name":"Yixian Xu","hidden":false},{"_id":"6a3ddcfb3b43e283349ec12b","name":"Yuxiang Chen","hidden":false},{"_id":"6a3ddcfb3b43e283349ec12c","name":"Zhendong Wang","hidden":false},{"_id":"6a3ddcfb3b43e283349ec12d","name":"Zihao Liu","hidden":false},{"_id":"6a3ddcfb3b43e283349ec12e","name":"Zikai Zhou","hidden":false},{"_id":"6a3ddcfb3b43e283349ec12f","name":"Huishuai Zhang","hidden":false},{"_id":"6a3ddcfb3b43e283349ec130","name":"Dongyan Zhao","hidden":false},{"_id":"6a3ddcfb3b43e283349ec131","name":"Chenfei Wu","hidden":false}],"publishedAt":"2026-06-25T00:00:00.000Z","submittedOnDailyAt":"2026-06-26T00:00:00.000Z","title":"Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation","submittedOnDailyBy":{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user","name":"taesiri"},"summary":"While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or dependent on up-to-date knowledge. We identify this challenge as the Context Gap: the mismatch between the user context and the sufficient generation context for T2I models. To bridge this gap, we propose Qwen-Image-Agent, a unified agentic framework that integrates plan, reason, search, memory and feedback in a context-centric manner. Qwen-Image-Agent treats user input as partial context and progressively constructs the generation context through Context-Aware Planning and Context Grounding. Specifically, Context-Aware Planning identifies missing context and plans how it should be acquired and used, while Context Grounding gathers this context from reason, search, memory, and feedback. To evaluate agentic image generation, we further introduce Image Agent Bench (IA-Bench), a benchmark covering four core image agent capabilities: Plan, Reason, Search, and Memory. Experiments on IA-Bench, Mindbench and WISE-Verified show that Qwen-Image-Agent outperforms strong baselines and achieves state-of-the-art performance.","upvotes":41,"discussionId":"6a3ddcfc3b43e283349ec132","ai_summary":"A unified agentic framework called Qwen-Image-Agent is proposed to address the context gap in text-to-image generation by progressively constructing complete generation context through planning, reasoning, searching, and memory mechanisms.","ai_keywords":["text-to-image models","context gap","agentic framework","context-aware planning","context grounding","image agent bench","image agent capabilities","plan","reason","search","memory"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"64c8b5837fe12ecd0a7e92eb","name":"Qwen","fullname":"Qwen","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"6039478ab3ecf716b1a5fd4d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6039478ab3ecf716b1a5fd4d/_Thy4E7taiSYBLKxEKJbT.jpeg","isPro":true,"fullname":"taesiri","user":"taesiri","type":"user"},{"_id":"64d14b2884f2058690051ed2","avatarUrl":"/avatars/f9cc6f0bdddfc2c17f4999e8a5646a5b.svg","isPro":false,"fullname":"Zekai Zhang","user":"JustinZekai","type":"user"},{"_id":"64a4ce8118f4e2529546daef","avatarUrl":"/avatars/6d88aa68eccfa07d2009df405f957fd7.svg","isPro":false,"fullname":"Jiang Lihan","user":"lhjiang","type":"user"},{"_id":"621d7baf411b802eb0b7060f","avatarUrl":"/avatars/738531a37b5dd6879231a5eb4b28227b.svg","isPro":false,"fullname":"Justin","user":"justinnlper","type":"user"},{"_id":"63c1699e40a26dd2db32400d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63c1699e40a26dd2db32400d/3N0-Zp8igv8-52mXAdiiq.jpeg","isPro":false,"fullname":"Chroma","user":"Chroma111","type":"user"},{"_id":"616fb788e2ad27af26561b1a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1675485317568-616fb788e2ad27af26561b1a.jpeg","isPro":false,"fullname":"Xiao Xu","user":"LooperXX","type":"user"},{"_id":"61454a989cd783fec339bdd0","avatarUrl":"/avatars/39cc15c0a70e0d2b1f1ef1c7a98e7db8.svg","isPro":false,"fullname":"Xi Yang","user":"ianyeung","type":"user"},{"_id":"657a6eed1ccc3c2a5ea7b585","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/RIQIF-JJdNI0SwJEq_9z7.jpeg","isPro":false,"fullname":"Jianzong Wu","user":"jianzongwu","type":"user"},{"_id":"643ff78cdc984afcbbbc3b1a","avatarUrl":"/avatars/eec5198ce88aaf8156840bec0d190a7f.svg","isPro":false,"fullname":"Yanwei Li","user":"YanweiLi","type":"user"},{"_id":"637f0eb22438d7485b8ef5d7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/637f0eb22438d7485b8ef5d7/70h7dekqj7LuBobOXckmJ.jpeg","isPro":false,"fullname":"Ming Li","user":"limingcv","type":"user"},{"_id":"6435c22e1860001f14436f2e","avatarUrl":"/avatars/83f4af7614c5a4612685391fbc994ab8.svg","isPro":false,"fullname":"Achilles ","user":"kira7x","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":3,"organization":{"_id":"64c8b5837fe12ecd0a7e92eb","name":"Qwen","fullname":"Qwen","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.26907.md","query":{}}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2606.26907 in a model README.md to link it from this page.

Cite arxiv.org/abs/2606.26907 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2606.26907 in a Space README.md to link it from this page.