DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914513876418560 |
|---|---|
| author | Yang, Hanqing Zhou, Qiang Du, Yongchao Zhou, Sashuai Wang, Zhibin Song, Jun Ge, Tiezheng Yu, Cheng Zheng, Bo |
| author_facet | Yang, Hanqing Zhou, Qiang Du, Yongchao Zhou, Sashuai Wang, Zhibin Song, Jun Ge, Tiezheng Yu, Cheng Zheng, Bo |
| contents | Recent image editing models have achieved strong visual fidelity but often struggle with tasks requiring complex reasoning. To investigate and enhance the reasoning-grounded planning for image editing, we propose DDA-Thinker, a Thinker-centric framework designed for the independent optimization of a planning module (Thinker) over a fixed generative model (Editor). This decoupled Thinker-centric paradigm facilitates a controlled analysis of the planning module and makes its contribution under a fixed Editor easier to assess. To effectively guide this Thinker, we introduce a dual-atomic reinforcement learning framework. This framework decomposes feedback into two distinct atomic rewards implemented through verifiable checklists: a cognitive-atomic reward to directly assess the quality of the Thinker's executable plan, which serves as the actionable outcome of the Thinker's reasoning, and a visual-atomic reward to assess the final image quality. To improve checklist quality, our checklist synthesis is grounded not only in the source image and user instruction but also in a rational reference description of the ideal post-edit scene. To support this training, we further develop a two-stage data curation pipeline that first synthesizes a diverse and reasoning-focused dataset, then applies difficulty-aware refinement to curate an effective training curriculum for reinforcement learning. Extensive experiments on reasoning-driven image editing benchmarks, including RISE-Bench and KRIS-Bench, demonstrate that our approach substantially improves overall performance. Our method enables a community model to achieve results competitive with strong proprietary models, highlighting the practical potential of Thinker-centric optimization under a fixed-editor setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25477 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing Yang, Hanqing Zhou, Qiang Du, Yongchao Zhou, Sashuai Wang, Zhibin Song, Jun Ge, Tiezheng Yu, Cheng Zheng, Bo Computer Vision and Pattern Recognition Artificial Intelligence Recent image editing models have achieved strong visual fidelity but often struggle with tasks requiring complex reasoning. To investigate and enhance the reasoning-grounded planning for image editing, we propose DDA-Thinker, a Thinker-centric framework designed for the independent optimization of a planning module (Thinker) over a fixed generative model (Editor). This decoupled Thinker-centric paradigm facilitates a controlled analysis of the planning module and makes its contribution under a fixed Editor easier to assess. To effectively guide this Thinker, we introduce a dual-atomic reinforcement learning framework. This framework decomposes feedback into two distinct atomic rewards implemented through verifiable checklists: a cognitive-atomic reward to directly assess the quality of the Thinker's executable plan, which serves as the actionable outcome of the Thinker's reasoning, and a visual-atomic reward to assess the final image quality. To improve checklist quality, our checklist synthesis is grounded not only in the source image and user instruction but also in a rational reference description of the ideal post-edit scene. To support this training, we further develop a two-stage data curation pipeline that first synthesizes a diverse and reasoning-focused dataset, then applies difficulty-aware refinement to curate an effective training curriculum for reinforcement learning. Extensive experiments on reasoning-driven image editing benchmarks, including RISE-Bench and KRIS-Bench, demonstrate that our approach substantially improves overall performance. Our method enables a community model to achieve results competitive with strong proprietary models, highlighting the practical potential of Thinker-centric optimization under a fixed-editor setting. |
| title | DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.25477 |