Evaluating the alignment between textual prompts and generated images is critical for ensuring the reliability and usability of text-to-image (T2I) models. However, most existing evaluation methods rely on coarse-grained metrics or static QA pipelines, which lack fine-grained interpretability and struggle to reflect human preferences. To address this, we propose REVEALER, a unified framework for element-level alignment evaluation based on reinforcement-guided visual reasoning. Adopting a structured "grounding-reasoning-conclusion" paradigm, our method enables Multimodal Large Language Models (MLLMs) to explicitly localize semantic elements and derive interpretable alignment judgments. We optimize the model via Group Relative Policy Optimization(GRPO) using a composite reward function that incorporates structural format, grounding accuracy, and alignment fidelity. Extensive experiments across four benchmarks-EvalMuse-40K, RichHF, MHaluBench, and GenAI-Bench-demonstrate that REVEALER achieves state-of-the-art performance. Our approach consistently outperforms both strong proprietary models and supervised baselines while demonstrating superior inference efficiency compared to existing iterative visual reasoning methods.

翻译：评估文本提示与生成图像之间的对齐关系对于确保文本到图像（T2I）模型的可靠性与可用性至关重要。然而，现有的大多数评估方法依赖于粗粒度指标或静态问答流程，这些方法缺乏细粒度的可解释性，且难以反映人类偏好。为解决此问题，我们提出了REVEALER，一个基于强化引导视觉推理的、用于细粒度元素级对齐评估的统一框架。该方法采用结构化的“定位-推理-结论”范式，使多模态大语言模型（MLLMs）能够显式地定位语义元素并得出可解释的对齐判断。我们通过组合奖励函数（包含结构格式、定位准确性和对齐保真度）并利用组相对策略优化（GRPO）对模型进行优化。在四个基准测试——EvalMuse-40K、RichHF、MHaluBench和GenAI-Bench——上的大量实验表明，REVEALER实现了最先进的性能。我们的方法在持续优于强大的专有模型和有监督基线模型的同时，相较于现有的迭代式视觉推理方法，还展现出更优越的推理效率。