CoT-RC: Chain-of-Thought Reflection and Correction for Image Generation without Extra Training

Lin Xu, Liang Han, Pengcheng Wan, Sensen Wang, Liqiang NieOpenReview 2026 · Submission to ICLR 2026 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Recent studies have explored integrating Chain-of-Thought (CoT) reasoning into image generation to improve accuracy and controllability. However, existing methods either rely on costly training, separate reasoning from generation, or lack fine-grained visual error correction. We propose a training-free CoT-enhanced image generation framework that leverages the semantic understanding and positional awareness of Unified Multimodal Models (UMMs). Our method introduces a CoT-guided Reflection Module for image-level global correction and a semantic-driven token-level local correction module for fine-grained refinement, forming a dynamic reasoning loop with iterative triggers and backtracking. Experiments demonstrate that our approach improves the Show-o baseline from 68\% to 78\% on GenEval and achieves a 14\% gain on T2I-CompBench, outperforming prior CoT-based methods under the same baseline, including reinforcement learning-based approaches. Our framework is entirely training-free, efficient, and establishes a new paradigm for CoT in image generation.
BibTeX
@misc{xu2026cot,
  author = {Lin Xu and Liang Han and Pengcheng Wan and Sensen Wang and Liqiang Nie},
  title = {{CoT-RC: Chain-of-Thought Reflection and Correction for Image Generation without Extra Training}},
  year = {2026},
  url = {https://openreview.net/forum?id=NO2m5hHuXy},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2026},
}

Loading related content...

Figure