AI 学会自己看自己画错在哪，再改到对
现在的多模态大模型能画图也能看图，理论上可以自己检查画得对不对、改、再看、再改。但难点在于：改完才知道有没有用，所以「反思的文字」和「改图的动作」必须一起学。以前的做法要么只优化改图的部分，要么只优化反思的部分，都浪费了大半潜力。这篇让同一个模型同时学反思和修改，用「同一张初始图的多条尝试路径」做对比，一次更新同时改进反思和改图，不需要外部裁判，自己就能闭环迭代。在 BAGEL 基准上比传统微调高了 12 分，而且这个能力能迁移到没训练过的其他基准上。它不是你明天就能用的工具，但这是 AI 从「生成一次就完事」走向「自己检查、自己改对」的关键一步。
📄 原文摘要(英文)
Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revision helps is known only after it is rendered, so the reflection text and the image generation must be learned jointly, over the whole loop. Supervised fine-tuning (SFT) on reflection trajectories gives a cold start but does not find the high-success repair paths, and naive RL that optimizes only the renderer or only one head leaves most of the gain untapped. We introduce UMM-Reflection, which applies reinforcement learning (RL) to complete reflection trajectories inside one unified model: sibling trajectories share one initial image, so the group-relative advantage compares reflection strategies, and one trajectory-level advantage updates both the reflection tokens and the flow-based revisions, avoiding the combinatorial blow-up of per-round credit assignment. Unlike single-round editing or pipelines with an external critic, credit flows across rounds and to both roles of the same model, and no verifier is needed at inference. On BAGEL, UMM-Reflection improves GenEval by 12.05 points over SFT, and the gains transfer to WISE (+10.97), OneIG-Bench (+3.48), and T2I-CompBench++ (+4.63), none of which is used in training.