MIRA: Multimodal Iterative Reasoning Agent for Image Editing
Abstract
MIRA, a multimodal reasoning agent, enhances diffusion-based image editing by iteratively interpreting complex instructions, improving both semantic consistency and perceptual quality.
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.
Community
The paper proposes a new agentic multimodal large language model (MLLM) designed for iterative, instruction-guided image editing.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Query-Kontext: An Unified Multimodal Model for Image Generation and Editing (2025)
- Factuality Matters: When Image Generation and Editing Meet Structured Visuals (2025)
- Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing (2025)
- EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing (2025)
- Are Image-to-Video Models Good Zero-Shot Image Editors? (2025)
- Plan-X: Instruct Video Generation via Semantic Planning (2025)
- ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper