{"slug": "omniverifier-c1-decomposed-graded-verifier-for-rule-governed-generative-world", "title": "OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling", "summary": "Researchers submitted a paper to arXiv on 15 Oct 2026 introducing OmniVerifier-C1, a decomposed graded visual verifier that replaces conventional True/False binary judgments with fine-grained pointwise scores for multimodal and rule-governed generative world modeling. The paper reports that the pointwise graded verifier significantly outperforms binary verifiers in traditional text-to-image scenarios, and that a Decoupled RL training strategy jointly optimizes sub-question-level binary judgment and global alignment scoring. The authors further show theoretically and empirically on Maze and Sudoku world-modeling tasks that a pairwise verification paradigm yields more accurate critiques than the pointwise formulation when ground-truth images are available.", "body_md": "# Computer Science > Computation and Language\n\n  [Submitted on 15 Oct 2026]\n\n# Title:OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling\n\n[View PDF](http://arxiv.org/pdf/2610.22355v1)\n\n[HTML (experimental)](https://arxiv.org/html/2610.22355v1)\n\nAbstract: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.\n    \n\n### Additional Features\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/omniverifier-c1-decomposed-graded-verifier-for-rule-governed-generative-world", "canonical_source": "http://arxiv.org/abs/2610.22355v1", "published_at": "2026-10-16 15:20:07+00:00", "updated_at": "2026-10-16 15:48:17.422305+00:00", "lang": "en", "topics": ["computer-vision", "generative-ai", "ai-research", "machine-learning", "large-language-models"], "entities": ["OmniVerifier-C1", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/omniverifier-c1-decomposed-graded-verifier-for-rule-governed-generative-world", "markdown": "https://wpnews.pro/news/omniverifier-c1-decomposed-graded-verifier-for-rule-governed-generative-world.md", "text": "https://wpnews.pro/news/omniverifier-c1-decomposed-graded-verifier-for-rule-governed-generative-world.txt", "jsonld": "https://wpnews.pro/news/omniverifier-c1-decomposed-graded-verifier-for-rule-governed-generative-world.jsonld"}}