IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection

• URL: http://arxiv.org/abs/2603.29602v1
• Date: Thu, 12 Feb 2026 02:37:38 GMT
• Title: IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection
• Abstract summary: IMAGAgent is a multi-turn image editing agent framework based on a "plan-execute-reflect" closed-loop mechanism.<n>It achieves deep synergy among instruction parsing, tool scheduling, and adaptive correction within a unified pipeline.<n>Experiments on our constructed textbfMTEditBench and the MagicBrush dataset demonstrate that IMAGAgent achieves performance significantly superior to existing methods.
• Score: 40.21337735524356
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are prone to error accumulation and semantic drift during multi-turn interactions, ultimately resulting in severe structural distortion of the generated images. For that, we propose \textbf{IMAGAgent}, a multi-turn image editing agent framework based on a "plan-execute-reflect" closed-loop mechanism that achieves deep synergy among instruction parsing, tool scheduling, and adaptive correction within a unified pipeline. Specifically, we first present a constraint-aware planning module that leverages a vision-language model (VLM) to precisely decompose complex natural language instructions into a series of executable sub-tasks, governed by target singularity, semantic atomicity, and visual perceptibility. Then, the tool-chain orchestration module dynamically constructs execution paths based on the current image, the current sub-task, and the historical context, enabling adaptive scheduling and collaborative operation among heterogeneous operation models covering image retrieval, segmentation, detection, and editing. Finally, we devise a multi-expert collaborative reflection mechanism where a central large language model (LLM) receives the image to be edited and synthesizes VLM critiques into holistic feedback, simultaneously triggering fine-grained self-correction and recording feedback outcomes to optimize future decisions. Extensive experiments on our constructed \textbf{MTEditBench} and the MagicBrush dataset demonstrate that IMAGAgent achieves performance significantly superior to existing methods in terms of instruction consistency, editing precision, and overall quality. The code is available at https://github.com/hackermmzz/IMAGAgent.git.

Related papers

• GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images [16.213122519512932]
  Real-world e-commerce image editing often requires multiple, localized, and auditable operations rather than global restyling.<n>Existing one-shot editors conflate intent resolution, spatial grounding, and synthesis into a single step.<n>We introduce GMO-E$2$DIT, an agentic editing framework that couples a Vision-Language Model (VLM) with a mask-conditioned image editor to tackle structured multi-turn task completion.
  arXiv  Detail & Related papers  (2026-07-01T13:23:45Z)
• SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution [61.612676324369595]
  We study whether image editing models can serve as sparse visual world models for robot manipulation.<n>We propose SWEET, a one-shot prediction visual planning framework.<n>Experiments on DROID and RoboMimic show that SWEET improves prediction across seen and unseen scenes.
  arXiv  Detail & Related papers  (2026-05-19T03:54:46Z)
• CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator [8.901958956012072]
  Conditional image editing is crucial in scenarios requiring strict structural control.<n>Most approaches rely on single-step generation.<n>We propose textbfCAMEO, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process.
  arXiv  Detail & Related papers  (2026-04-03T16:27:02Z)
• ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning [20.61925053714293]
  Image editing systems often struggle with complex, indirect, or multi-step user instructions.<n>We propose ImageEdit-R1, a multi-agent framework for intelligent image editing.<n>Our method treats image editing as a sequential decision-making problem, enabling dynamic and context-aware editing strategies.
  arXiv  Detail & Related papers  (2026-03-09T07:50:14Z)
• I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing [59.434028565445885]
  I2E is a novel "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment.<n>I2E utilizes a Decomposer to transform unstructured images into discrete, manipulable object layers and then introduces a physics-aware Vision-Language-Action Agent to parse complex instructions.<n>I2E significantly outperforms state-of-the-art methods in handling complex compositional instructions, maintaining physical plausibility, and ensuring multi-turn editing stability.
  arXiv  Detail & Related papers  (2026-01-07T09:29:57Z)
• MIRA: Multimodal Iterative Reasoning Agent for Image Editing [48.41212094929379]
  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.
  arXiv  Detail & Related papers  (2025-11-26T06:13:32Z)
• EditInfinity: Image Editing with Binary-Quantized Generative Models [64.05135380710749]
  We investigate the parameter-efficient adaptation of binary-quantized generative models for image editing.<n>Specifically, we propose EditInfinity, which adapts emphInfinity, a binary-quantized generative model, for image editing.<n>We propose an efficient yet effective image inversion mechanism that integrates text prompting rectification and image style preservation.
  arXiv  Detail & Related papers  (2025-10-23T05:06:24Z)
• Does the Manipulation Process Matter? RITA: Reasoning Composite Image Manipulations via Reversely-Ordered Incremental-Transition Autoregression [13.933194190556714]
  We reformulate image manipulation localization as a conditional sequence prediction task, proposing the RITA framework.<n>RITA predicts manipulated regions layer-by-layer in an ordered manner, using each step's prediction as the condition for the next.<n>To enable training and evaluation, we synthesize multi-step manipulation data and construct a new benchmark HSIM.
  arXiv  Detail & Related papers  (2025-09-24T11:25:44Z)
• Marmot: Object-Level Self-Correction via Multi-Agent Reasoning [55.74860093731475]
  Marmot is a novel and generalizable framework that leverages Multi-Agent Reasoning for Multi-Object Self-Correcting.<n>Marmot significantly improves accuracy in object counting, attribute assignment, and spatial relationships for image generation tasks.
  arXiv  Detail & Related papers  (2025-04-10T16:54:28Z)

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.