Paper page - From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing

Source: https://huggingface.co/papers/2605.15181

Abstract

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.

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 aplannergenerates structuredatomic decompositionsand anorchestratorselects tools and regions to execute each step. Avision language judgeprovides outcome-based rewards forinstruction adherenceandvisual quality. Theorchestratoris trained to maximize these rewards, and successful trajectories are used to refine theplanner. By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2605\.15181

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

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

Datasets citing this paper0

No dataset linking this paper

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

Spaces citing this paper0

No Space linking this paper

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

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.