Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address this, we propose UniReason, a unified framework that harmonizes these two tasks through two complementary reasoning paradigms. We incorporate world knowledge-enhanced textual reasoning into generation to infer implicit knowledge, and leverage editing capabilities for fine-grained editing-like visual refinement to further correct visual errors via self-reflection. This approach unifies generation and editing within a shared architecture, mirroring the human cognitive process of planning followed by refinement. We support this framework by systematically constructing a large-scale reasoning-centric dataset (~300k samples) covering five major knowledge domains (e.g., cultural commonsense, physics, etc.) for textual reasoning, alongside an agent-generated corpus for visual refinement. Extensive experiments demonstrate that UniReason achieves advanced performance on reasoning-intensive benchmarks such as WISE, KrisBench and UniREditBench, while maintaining superior general synthesis capabilities.
@article{arxiv.2602.02437,
title = {UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing},
author = {Dianyi Wang and Chaofan Ma and Feng Han and Size Wu and Wei Song and Yibin Wang and Zhixiong Zhang and Tianhang Wang and Siyuan Wang and Zhongyu Wei and Jiaqi Wang},
journal= {arXiv preprint arXiv:2602.02437},
year = {2026}
}