M3：通过多模态、多智能体和多轮视觉推理实现高保真的文本到图像生成
M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning
AI总结：
M3通过多智能体和多轮视觉推理提升开源模型的文本到图像生成能力，超越商业系统并实现最先进的性能。
摘要：
生成模型在文本到图像合成中实现了令人印象深刻的保真度，但在涉及多个约束的复杂组合提示中却面临困难。我们介绍了M3（多模态、多智能体、多轮），这是一个无需训练的框架，通过迭代推理时间的细化系统性地解决这些失败。M3在稳健的多智能体循环中协调现成的基础模型：规划器将提示分解为可验证的检查清单，而专门的检查员、细化器和编辑器智能体逐一精确纠正约束，验证器确保单调改进。应用于开源模型，M3在具有挑战性的OneIG-EN基准上取得了显著成果，我们的Qwen-Image+M3超越了商业旗舰系统，包括Imagen4（0.515）和Seedream 3.0（0.530），达到最先进的性能（0.532总体）。这表明智能多智能体推理可以将开源模型提升到专有替代品之上。M3还显著提高了GenEval组合指标，在强化测试集上有效将空间推理性能翻倍。作为兼容任何预训练T2I模型的即插即用模块，M3在无需昂贵重新训练的情况下建立了新的组合生成范式。
英文摘要：
Generative models have achieved impressive fidelity in text-to-image synthesis, yet struggle with complex compositional prompts involving multiple constraints. We introduce \textbf{M3 (Multi-Modal, Multi-Agent, Multi-Round)}, a training-free framework that systematically resolves these failures through iterative inference-time refinement. M3 orchestrates off-the-shelf foundation models in a robust multi-agent loop: a Planner decomposes prompts into verifiable checklists, while specialized Checker, Refiner, and Editor agents surgically correct constraints one at a time, with a Verifier ensuring monotonic improvement. Applied to open-source models, M3 achieves remarkable results on the challenging OneIG-EN benchmark, with our Qwen-Image+M3 surpassing commercial flagship systems including Imagen4 (0.515) and Seedream 3.0 (0.530), reaching state-of-the-art performance (0.532 overall). This demonstrates that intelligent multi-agent reasoning can elevate open-source models beyond proprietary alternatives. M3 also substantially improves GenEval compositional metrics, effectively doubling spatial reasoning performance on hardened test sets. As a plug-and-play module compatible with any pre-trained T2I model, M3 establishes a new paradigm for compositional generation without costly retraining.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
