OmniVerifier-C1：面向规则驱动生成式世界建模的分解式分级验证器
OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling
AI总结：
该研究提出OmniVerifier-C1分解式分级验证器，采用解耦式RL策略训练，在文本到图像、迷宫与数独等任务中，其性能优于传统二元验证器，为生成式模型向结构化世界建模智能体过渡提供关键支撑。
摘要：
生成式视觉验证器在推进多模态智能方面发挥着关键作用。为提升视觉验证器在涉及组合需求的复杂多模态场景中的鲁棒性，我们突破仅输出“真/假”离散判断的传统二元验证器，引入一种可自动将复杂提示或环境规则分解为细粒度组件，并为各组件分配逐点分数以提供连续且更具信息量的评判信号的验证器。我们的实验进一步表明，这些结构化且可解释的输出可提升验证器对域外多模态评判任务的泛化能力。为训练该验证器，我们提出一种解耦式强化学习（RL）训练策略，该策略联合优化子问题级二元判断与全局对齐评分，利用精确的局部反馈开发细粒度验证能力，为全局层面可靠的连续评分奠定基础。在通用强化学习框架下，我们首先在传统文本到图像场景中实证表明，所提出的逐点分级验证器显著优于二元验证器；随后将研究扩展至规则驱动的生成式世界建模场景，其中生成式模型被用于在显式规则下进行世界模拟与世界推理。从理论角度，我们进一步证明，当存在真实图像时，成对验证范式相比逐点公式能产生更准确的评判；在迷宫（Maze）、数独（Sudoku）等多种结构化世界建模任务上的实证结果进一步验证了我们方法的有效性。总体而言，我们的发现揭示了一个关键洞见：从生成式模型向结构化世界建模智能体的过渡，关键依赖于准确的成对分级视觉验证器的可用性。
英文摘要：
Generative visual verifiers play a crucial role in advancing multimodal intelligence. To enhance the robustness of visual verifiers in complex multimodal scenarios involving compositional requirements, we move beyond conventional binary verifiers that produce only True/False discrete judgments and introduce a verifier that automatically decomposes complex prompts or environmental rules into fine-grained components and assigns pointwise scores to provide a continuous and more informative critique signal. Our experiments further demonstrate that these structured and interpretable outputs improve the verifier's generalization to out-of-domain multimodal critic tasks. To train this verifier, we introduce a Decoupled RL training strategy that jointly optimizes sub-question-level binary judgment and global alignment scoring, using precise local feedback to develop fine-grained verification capabilities that provide a foundation for reliable continuous scoring at the global level. Under a general reinforcement learning framework, we first empirically demonstrate that the proposed pointwise graded verifier significantly outperforms binary verifiers in traditional text-to-image scenarios. We then extend our investigation to rule-governed generative world modeling where generative models are leveraged for world simulation and world reasoning under explicit rules. From a theoretical standpoint, we further show that a pairwise verification paradigm yields more accurate critiques than the pointwise formulation when ground-truth images are available, with empirical results on diverse structured world-modeling tasks such as Maze and Sudoku further validating the effectiveness of our approach. Overall, our findings suggest a key insight: the transition from generative models to structured world-modeling agents critically hinges on the availability of accurate pairwise graded visual verifiers.
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。
