mlsanityData to 14 Oct 2026

SMART-Editor: A Multi-Agent Framework for Human-Like Design Editing with Structural Integrity

arXiv 2507.23095 ↗First posted 30 Jul 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We present SMART-Editor, a framework for compositional layout and content editing across structured (posters, websites) and unstructured (natural images) domains. Unlike prior models that perform local edits, SMART-Editor preserves global coherence through two strategies: Reward-Refine, an inference-time rewardguided refinement method, and RewardDPO, a training-time preference optimization approach using reward-aligned layout pairs. To evaluate model performance, we introduce SMARTEdit-Bench, a benchmark covering multi-domain, cascading edit scenarios. SMART-Editor outperforms strong baselines like InstructPix2Pix and HIVE, with RewardDPO achieving up to 15% gains in structured settings and Reward-Refine showing advantages on natural images. Automatic and human evaluations confirm the value of reward-guided planning in producing semantically consistent and visually aligned edits.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 45 references that are in the map. First posted on arXiv 30 Jul 2025.

Builds on

34 of 45 references.

References · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  6. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  7. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 624
  8. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 498
  9. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 294
  10. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 219
  11. 2024HQ-Edit: A High-Quality Dataset for Instruction-based Image Editingcited by 193
  12. 2023HIVE: Harnessing Human Feedback for Instructional Visual Editingcited by 173
22 more
  1. 2024Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineeringcited by 152
  2. 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generationcited by 143
  3. 2024GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editingcited by 133
  4. 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 131
  5. 2024Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detectioncited by 122
  6. 2019LayoutVAE: Stochastic Scene Layout Generation From a Label Setcited by 119
  7. 2024SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editingcited by 97
  8. 2023InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructionscited by 64
  9. 2023LayoutDM: Transformer-based Diffusion Model for Layout Generationcited by 57
  10. 2023LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Promptscited by 54
  11. 2023COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Designcited by 43
  12. 2025PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Frameworkcited by 40
  13. 2023Text-Driven Image Editing via Learnable Regionscited by 31
  14. 2024HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editingcited by 29
  15. 2025CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generationcited by 19
  16. 2025PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generationcited by 16
  17. 2024SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posterscited by 14
  18. 2024Automatic Layout Planning for Visually-Rich Documents with Instruction-Following Modelscited by 7
  19. 2024DocEdit-v2: Document Structure Editing Via Multimodal LLM Groundingcited by 7
  20. 2025GraphicBench: A Planning Benchmark for Graphic Design with Language Agentscited by 4
  21. 2013Ethics of using language editing services in an era of digital communication and heavily multiauthored paperscited by 1
  22. 2022EDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verificationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization
  2. 2026InfoEdit: Probing Global Layout Reasoning in Infographic Editing
  3. 2026ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation
  4. 2026RewardHarness: Self-Evolving Agentic Post-Training
  5. 2026EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement
  6. 2026Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
  7. 2026SLIDEFORGE: An LLM Agent for Controllable Editing of Slides as Structured Artifacts
  8. 2026ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition