arXiv cs.CL· Bowei Liu, Xinchen Zhang, Xuhuan Li, Tianlin Zhang, Kaian Jiang, Jingwei Liu, Congyang Zhao, Yifei Qian, Junhong Liu, Zhiheng Li, Yujiu Yang, Yang Cai, Ling Yang·· 2 天前AI 评分29
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 导读
研究团队提出 OmniVerifier-C1，将传统只输出 True/False 的二值视觉验证器改为自动把复杂提示词或环境规则拆解为细粒度子问题并逐项打分的分级验证器，输出连续且可解释的评判信号。
正文 · 原文
Authors:Bowei Liu, Xinchen Zhang, Xuhuan Li, Tianlin Zhang, Kaian Jiang, Jingwei Liu, Congyang Zhao, Yifei Qian, Junhong Liu, Zhiheng Li, Yujiu Yang, Yang Cai, Ling Yang
Abstract: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.
| Comments: | NeurIPS 2026. Project: this https URL |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22355 [cs.CL] |
| (or arXiv:2610.22355v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22355 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bowei Liu [view email]
[v1]
Thu, 15 Oct 2026 17:58:04 UTC (9,110 KB)
来源：arXiv cs.CL · arxiv.org