MIRA: Multimodal Iterative Reasoning Agent for Image Editing

• URL: http://arxiv.org/abs/2511.21087v1
• Date: Wed, 26 Nov 2025 06:13:32 GMT
• Title: MIRA: Multimodal Iterative Reasoning Agent for Image Editing
• Authors: Ziyun Zeng, Hang Hua, Jiebo Luo,
• Abstract summary: We propose MIRA (Multimodal Iterative Reasoning Agent), a lightweight, plug-and-play multimodal reasoning agent.<n>Instead of issuing a single prompt or static plan, MIRA predicts atomic edit instructions step by step, using visual feedback to make its decisions.<n>Our 150K multimodal tool-use dataset, MIRA-Editing, combined with a two-stage SFT + GRPO training pipeline, enables MIRA to perform reasoning and editing over complex editing instructions.
• Score: 48.41212094929379
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Instruction-guided image editing offers an intuitive way for users to edit images with natural language. However, diffusion-based editing models often struggle to accurately interpret complex user instructions, especially those involving compositional relationships, contextual cues, or referring expressions, leading to edits that drift semantically or fail to reflect the intended changes. We tackle this problem by proposing MIRA (Multimodal Iterative Reasoning Agent), a lightweight, plug-and-play multimodal reasoning agent that performs editing through an iterative perception-reasoning-action loop, effectively simulating multi-turn human-model interaction processes. Instead of issuing a single prompt or static plan, MIRA predicts atomic edit instructions step by step, using visual feedback to make its decisions. Our 150K multimodal tool-use dataset, MIRA-Editing, combined with a two-stage SFT + GRPO training pipeline, enables MIRA to perform reasoning and editing over complex editing instructions. When paired with open-source image editing models such as Flux.1-Kontext, Step1X-Edit, and Qwen-Image-Edit, MIRA significantly improves both semantic consistency and perceptual quality, achieving performance comparable to or exceeding proprietary systems such as GPT-Image and Nano-Banana.

Related papers

• TalkPhoto: A Versatile Training-Free Conversational Assistant for Intelligent Image Editing [21.708181904910177]
  Multimodal Large Language Models (MLLMs) promote information exchange between instructions and images.<n>These frameworks often build a multi-instruction dataset to train the model to handle multiple editing tasks.<n>We present TalkPhoto, a versatile training-free image editing framework that facilitates precise image manipulation through conversational interaction.
  arXiv  Detail & Related papers  (2026-01-05T09:00:32Z)
• Image Editing As Programs with Diffusion Models [69.05164729625052]
  We introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture.<n>IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations.<n>Our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions.
  arXiv  Detail & Related papers  (2025-06-04T16:57:24Z)
• FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model [54.693572837423226]
  FireEdit is an innovative Fine-grained Instruction-based image editing framework that exploits a REgion-aware VLM.<n>FireEdit is designed to accurately comprehend user instructions and ensure effective control over the editing process.<n>Our approach surpasses the state-of-the-art instruction-based image editing methods.
  arXiv  Detail & Related papers  (2025-03-25T16:59:42Z)
• BrushEdit: All-In-One Image Inpainting and Editing [76.93556996538398]
  BrushEdit is a novel inpainting-based instruction-guided image editing paradigm.<n>We devise a system enabling free-form instruction editing by integrating MLLMs and a dual-branch image inpainting model.<n>Our framework effectively combines MLLMs and inpainting models, achieving superior performance across seven metrics.
  arXiv  Detail & Related papers  (2024-12-13T17:58:06Z)
• SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models [91.22477798288003]
  This paper introduces SmartEdit, a novel approach to instruction-based image editing. It exploits Multimodal Large Language Models (MLLMs) to enhance their understanding and reasoning capabilities. We show that a small amount of complex instruction editing data can effectively stimulate SmartEdit's editing capabilities for more complex instructions.
  arXiv  Detail & Related papers  (2023-12-11T17:54:11Z)
• Guiding Instruction-based Image Editing via Multimodal Large Language Models [102.82211398699644]
  Multimodal large language models (MLLMs) show promising capabilities in cross-modal understanding and visual-aware response generation. We investigate how MLLMs facilitate edit instructions and present MLLM-Guided Image Editing (MGIE) MGIE learns to derive expressive instructions and provides explicit guidance.
  arXiv  Detail & Related papers  (2023-09-29T10:01:50Z)
• LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance [0.0]
  LEDITS is a combined lightweight approach for real-image editing, incorporating the Edit Friendly DDPM inversion technique with Semantic Guidance. This approach achieves versatile edits, both subtle and extensive as well as alterations in composition and style, while requiring no optimization nor extensions to the architecture.
  arXiv  Detail & Related papers  (2023-07-02T09:11:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.