MLIE-CoT: Chain-of-Thought Reasoning via Multi-Level Image Editing

Baichuan Yang, Dongyuan Xu, Zhao Yang, Yong Liu, Bing SuarXiv 2026 · arXiv

TL;DR

MLIE-CoT is a visual "Chain-of-Thought" framework that improves text-to-image generation by iteratively diagnosing and repairing images at multiple levels of granularity. By training a specialized router to choose between local edits, global refinements, or full regenerations, the system preserves correct visual details while systematically fixing compositional errors, outperforming state-of-the-art models like FLUX.2 on complex benchmarks.

What Problem Does This Paper Address?

Despite the impressive quality of modern text-to-image (T2I) models, they frequently stumble on complex, compositional prompts. Common failures include missing objects, incorrect attribute binding (e.g., a "red hat and blue shirt" becoming a "blue hat and red shirt"), and reversed spatial relationships.

Existing "Chain-of-Thought" (CoT) approaches for images typically rely on textual reasoning or repeated whole-image regeneration. However, these methods face two major hurdles:

  1. Negative Visual Anchors: If an initial image has a fundamentally broken layout, using it as a condition for the next step often carries those errors forward, leading to accumulated hallucinations.
  2. Collateral Damage: Attempting to fix a small detail via whole-image editing often inadvertently changes parts of the image that were already correct.
Figure 1: Failure cases caused by negative visual anchors and collateral changes during image-conditioned repair.

Methods

The authors propose MLIE-CoT (Multi-Level Image Editing Chain-of-Thought), a framework that treats image generation as a test-time control process. The pipeline follows a loop: Analyze → Route → Plan → Edit → Review.

The core innovation is the Multi-Level Repair strategy, which allows the model to choose the "intervention strength" based on the severity of the error:

  • L1 (Local Repair): Uses bounding boxes and crops to focus the editor on specific regions (e.g., changing a pizza's color). This minimizes disruption to the rest of the scene.
  • L2 (Whole-Image Editing): Adjusts global attributes like background or spatial relations while keeping the general layout.
  • L3 (Text-Only Regeneration): Discards the current image entirely and starts fresh if the current state is a "negative anchor" that would mislead further edits.
Overview of the MLIE-CoT framework, showing the routing between L1, L2, and L3 repair paths.

To make this work, they trained a Repair-Level Router using a frozen Qwen3.5-9B multimodal backbone. Unlike simple classifiers, this router is trained using Utility-Supervised Learning, where it learns to predict which repair level will yield the highest "utility"—a score balancing error correction, content preservation, and computational cost.

Datasets

  • Training Dataset: The authors constructed a custom image-repair dataset consisting of 14.8K images derived from 1K prompt families. They intentionally created "controlled errors" by perturbing prompts to generate mismatched images, providing clear ground truth for what needs fixing.
  • Evaluation Benchmarks:
    • GenEval: A benchmark for compositional consistency (objects, counts, colors, positions).
  • WISE: A challenging dataset requiring implicit knowledge (e.g., generating an image based on a scientific or cultural clue rather than a direct description).

Key Insights and Ideas

  • Granularity is the Key to Preservation: The "aha moment" here is that the model shouldn't always look at the whole image. By using local crops (L1), the model can fix a single object's color without changing the background, a common failure in standard diffusion editing.
  • Routing vs. LLM Prompting: Simply asking an LLM to "fix the image" is often unstable. By training a router on actual utility scores (how much an action actually improved the image in practice), the system becomes much more reliable at choosing the right tool for the job.
  • Visual States as Reasoning: In MLIE-CoT, the intermediate images are not just outputs; they are the "thoughts" in the chain. The framework treats these images as reusable states that can be accepted, modified, or rejected.
Examples of L1, L2, and L3 repairs, showing how different error types favor different granularities.

Key Results

MLIE-CoT demonstrated significant gains across multiple base models:

  • GenEval: Improved BAGEL from 0.80 to 0.86 and FLUX.2-dev from 0.84 to 0.88 in overall accuracy. The gains were most prominent in difficult categories like spatial positioning and attribute binding.
  • WISE: Raised the overall score from 0.70 to 0.76 (BAGEL) and 0.73 to 0.78 (FLUX.2).
  • Efficiency: Ablation studies showed that 1–3 repair steps offer the best trade-off between quality and cost. Beyond three steps, the gains tend to plateau as the model hits the inherent capacity limits of the underlying generator.
Performance curves showing how image quality improves over multiple CoT steps before reaching a ceiling.

Limitations and Future Work

  • Resolution Constraints: The current framework operates at fixed resolutions (e.g., 1024x1024). Extending this to higher resolutions or variable aspect ratios remains a challenge.
  • Prompt Optimization: While the router selects the level of repair, the specific textual instructions sent to the editor could be further optimized to reduce ambiguity.
  • Computational Overhead: Although more efficient than exhaustive search, iterative editing still requires multiple forward passes, which may be too slow for real-time applications without further optimization.

Summary updated

Abstract

Chain-of-thought (CoT) reasoning has proven effective in improving the reasoning abilities of large language models by breaking complex tasks into step-by-step solutions. In recent years, researchers have attempted to extend CoT reasoning to visual generative models to improve their ability to handle complex tasks. However, existing CoT methods for text-to-image generation still rely mainly on textual reasoning and therefore cannot fully use and preserve the correct semantic information already present in an image, as even the most detailed language cannot capture all visual information. With advances in image generation, models such as FLUX and BAGEL can generate images conditioned on visual inputs. Recent work has attempted to carry images forward as context in the chain of thought, but this introduces another limitation: unsuitable earlier images can strongly interfere with the model, while repeated whole-image regeneration introduces new hallucinations at each round and causes them to accumulate. To address these issues, we propose MLIE-CoT, a visual chain-of-thought framework based on multi-level image editing. MLIE-CoT learns to select the repair granularity from three levels, preserving correct semantics whenever possible during reasoning while reducing the effect of incorrect content. To improve the ability of multimodal models to route errors of different severity to appropriate repair levels, we construct an image-repair dataset covering different error cases and use it to train a repair-level router. Extensive experiments demonstrate that MLIE-CoT significantly outperforms both its base models and methods using fixed repair strategies, producing clear improvements across multiple benchmarks.
BibTeX
@misc{yang2026mlie,
  author = {Baichuan Yang and Dongyuan Xu and Zhao Yang and Yong Liu and Bing Su},
  title = {{MLIE-CoT: Chain-of-Thought Reasoning via Multi-Level Image Editing}},
  year = {2026},
  eprint = {2611.24433},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.24433},
}
Figure