AI 终于会接话茬了：你画完图，它知道下一步该改哪
聊天助手现在能陪你聊文字，但当你用 AI 画图时，它往往只会干等你说下一句。这篇来自 Qwen App 的研究发现，在 10 万段真实的画图对话里，80% 的后续建议都依赖当前图片——也就是说，AI 得先看懂你画了什么，才能提出有用的下一步。他们搭了一套三阶段系统：先用真实数据教模型哪些编辑意图是合理的，再用你的点击反馈调优，最后加一道视觉检查，确保它建议的改动不会和画面打架。上线后，视觉不一致率从 3.7% 降到 0.9%，推荐点击率涨了 32.7%，用户平均对话轮数多了近四成。这不是你明天就能用上的功能，但它说明：AI 正在从『听指令』进化到『懂语境』，而画图对话是它学会接话茬的第一站。
📄 原文摘要(英文)
Conversational assistants increasingly recommend follow-up edits to help users continue a task. Existing systems primarily target text-only interactions, leaving image-creation conversations underexplored. In image-creation tasks, useful follow-up edit suggestions must reflect user preferences, offer diverse directions, and remain executable on the current image. We collected 100,000 real multi-turn image-creation conversation samples from Qwen App and found that 80.1% are image-dependent, underscoring the need for multimodal recommendation. We address this setting with a three-stage framework. In Stage 1, we use real online data to build a human-reviewed table of appropriate follow-up editing intents, then create SFT targets and fine-tune a multimodal policy. In Stage 2, to align rule-guided SFT suggestions with actual user choices, we use user click feedback to optimize the policy through multi-objective reinforcement learning. In Stage 3, to reduce visual inconsistencies between suggested edits and the current image, we introduce a visual verifier as additional training supervision. Extensive experiments demonstrate that our framework significantly outperforms baselines on both automatic and human evaluations. In a live user-randomized A/B test with millions of users, our final framework reduces visual inconsistency from 3.7% to 0.9%. Furthermore, it significantly improves recommendation CTR by 32.70%, image take-away rate by 16.32%, and average conversation turns per user by 39.90% (all p<0.05).