Proposes an experiential learning framework for long-horizon, open-ended image editing. Instead of relying on static teacher imitation, the system actively learns optimal tool and region selection through trial and error. It couples a structured task planner with an orchestrator trained via outcome-based rewards from a vision-language judge, leading to highly coherent and reliable multi-step edits.</p>\n","updatedAt":"2026-05-18T05:19:04.457Z","author":{"_id":"6496b347b8d4efc75b02e2fa","avatarUrl":"/avatars/2aa6b168e5d1aeb7b9e3481c826450a5.svg","fullname":"Anirudh Sundara Rajan","name":"AniSundar18","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9239366054534912},"editors":["AniSundar18"],"editorAvatarUrls":["/avatars/2aa6b168e5d1aeb7b9e3481c826450a5.svg"],"reactions":[{"reaction":"🔥","users":["jpark677"],"count":1}],"isReport":false}},{"id":"6a0bc1017415cddaa300bb0b","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":357,"isUserFollowing":false},"createdAt":"2026-05-19T01:46:41.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator](https://huggingface.co/papers/2604.03156) (2026)\n* [EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement](https://huggingface.co/papers/2605.07457) (2026)\n* [Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions](https://huggingface.co/papers/2604.15917) (2026)\n* [Leveraging Verifier-Based Reinforcement Learning in Image Editing](https://huggingface.co/papers/2604.27505) (2026)\n* [MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing](https://huggingface.co/papers/2604.05180) (2026)\n* [DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing](https://huggingface.co/papers/2604.25477) (2026)\n* [EditTransfer++: Toward Faithful and Efficient Visual-Prompt-Guided Image Editing](https://huggingface.co/papers/2605.07455) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2604.03156\">CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.07457\">EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.15917\">Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.27505\">Leveraging Verifier-Based Reinforcement Learning in Image Editing</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.05180\">MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.25477\">DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.07455\">EditTransfer++: Toward Faithful and Efficient Visual-Prompt-Guided Image Editing</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code><span class=\"SVELTE_PARTIAL_HYDRATER contents\" data-target=\"UserMention\" data-props=\"{&quot;user&quot;:&quot;librarian-bot&quot;}\"><span class=\"inline-block\"><span class=\"contents\"><a href=\"/librarian-bot\">@<span class=\"underline\">librarian-bot</span></a></span> </span></span> recommend</code></p>\n","updatedAt":"2026-05-19T01:46:41.755Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":357,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7076845765113831},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.15181","authors":[{"_id":"6a0aa00075184a0d71e02700","name":"Anirudh Sundara Rajan","hidden":false},{"_id":"6a0aa00075184a0d71e02701","name":"Krishna Kumar Singh","hidden":false},{"_id":"6a0aa00075184a0d71e02702","name":"Yong Jae Lee","hidden":false}],"publishedAt":"2026-05-14T00:00:00.000Z","submittedOnDailyAt":"2026-05-18T00:00:00.000Z","title":"From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing","submittedOnDailyBy":{"_id":"6496b347b8d4efc75b02e2fa","avatarUrl":"/avatars/2aa6b168e5d1aeb7b9e3481c826450a5.svg","isPro":false,"fullname":"Anirudh Sundara Rajan","user":"AniSundar18","type":"user","name":"AniSundar18"},"summary":"Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for instruction adherence and visual quality. The orchestrator is trained to maximize these rewards, and successful trajectories are used to refine the planner. By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.","upvotes":9,"discussionId":"6a0aa00075184a0d71e02703","projectPage":"https://anisundar18.github.io/Plan2Pix.github.io/","ai_summary":"An experiential framework for long-horizon image editing that couples planning with reward-driven execution to improve coherence and reliability of complex multi-step edits.","ai_keywords":["planner","orchestrator","vision language judge","reward-driven execution","atomic decompositions","tool selection","region selection","instruction adherence","visual quality"],"organization":{"_id":"61d090ec03bc10eb8e1c2970","name":"uw-madison","fullname":"University of Wisconsin - Madison","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/IYmUaLUc_rDVNC6F7-k8M.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"68c87b5dadd99c675f3bbf00","avatarUrl":"/avatars/589d883d1b332be60eab3fb869bb926d.svg","isPro":false,"fullname":"Yong Jae Lee","user":"yongl-adobe","type":"user"},{"_id":"660047c56ab19a1d21e9d764","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/PFPd87Uh5Z3Y5WoCnJqIx.png","isPro":false,"fullname":"Le Thien Phuc Nguyen","user":"plnguyen2908","type":"user"},{"_id":"63b7b2c6bd2d153522821766","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63b7b2c6bd2d153522821766/aHtga-_OUdOrg_TRrXO08.jpeg","isPro":false,"fullname":"Mu Cai","user":"mucai","type":"user"},{"_id":"677f8ec859ee993c8379d2a7","avatarUrl":"/avatars/e75ef1d17e8e4c8777a2818be281ac4e.svg","isPro":false,"fullname":"Hyunjung Lee","user":"hyulee","type":"user"},{"_id":"631dd9e20db849840ab53dc8","avatarUrl":"/avatars/9697d389e18e97ffa66c3e779cd1ac45.svg","isPro":false,"fullname":"Tofte Schøn","user":"Danieltsx12","type":"user"},{"_id":"64af72d4a609b29cc7b5919b","avatarUrl":"/avatars/bc33b6bfa6995ea953f71366184f19d3.svg","isPro":false,"fullname":"Aniket Rege","user":"aniketr","type":"user"},{"_id":"6508b164abdde5290e5e4939","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6508b164abdde5290e5e4939/lQgAs3BHwCyI7Go1QA62m.jpeg","isPro":false,"fullname":"Harris Zhang","user":"HanSolo9682","type":"user"},{"_id":"634ef841de30ee20582b355a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/634ef841de30ee20582b355a/7W9HHzEjURmUPkQ7U_Nnl.png","isPro":true,"fullname":"Thao Nguyen","user":"thaoshibe","type":"user"},{"_id":"670f5267d1b58394145c1ca3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/t-YchgvZCbDW-plR8DZbA.png","isPro":false,"fullname":"Jaden Park","user":"jpark677","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"61d090ec03bc10eb8e1c2970","name":"uw-madison","fullname":"University of Wisconsin - Madison","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e396f2b5bb631e9b2fac9a/IYmUaLUc_rDVNC6F7-k8M.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.15181.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2605.15181 in a model README.md to link it from this page.

Cite arxiv.org/abs/2605.15181 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2605.15181 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.