cs.CVNov 18, 2026

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

Authors: Baichuan Yang, Dongyuan Xu, Zhao Yang, Yong Liu, Bing Su

Organizations: Renmin University of China, Beijing · Zhongguancun Academy

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.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations

    Jun 15, 2026Zhiqiang Zhou, Junliang Dai, Xu lingVLM InterpretabilityMultimodal CoT Reasoning

  2. IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

    Jun 23, 2026Zixuan Li, Haokun Lin, Yicheng Xiao +10T2I GenerationMultimodal Large Language Models

  3. TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding

    Jun 7, 2026Lianyu Hu, Xiaoyu Ma, Zeqin Liao +1Multimodal Large Language ModelsMultimodal Reasoning