{"slug": "vira-toward-ultra-high-resolution-visual-agents-via-cross-input-relative-policy", "title": "ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization", "summary": "A paper submitted to arXiv on 16 Nov 2026 proposes Cross-Input Relative Policy Optimization (CrossRPO), a reinforcement learning method that trains visual agents on contrast sets — one question asked about several versions of an image that differ only in a small evidence region with different answers — so that only reading the evidence solves the whole set. The authors report CrossRPO reaches 63.3% set accuracy on ViRA-Bench at maximum resolution versus 59.3% for GRPO, using contrast sets built from 21- to 120-megapixel images and training ViRA-9B and ViRA-27B on only about 3,500 ViRA-Train items each. The authors state ViRA-9B is the most accurate open model of its size on all benchmarks and ViRA-27B outperforms Claude Haiku 5.5 and GPT-6-Luna, both at their highest thinking level, on most benchmarks.", "body_md": "# Computer Science > Computer Vision and Pattern Recognition\n\n  [Submitted on 16 Nov 2026]\n\n# Title:ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization\n\n[View PDF](http://arxiv.org/pdf/2611.21605v1)\n\n[HTML (experimental)](https://arxiv.org/html/2611.21605v1)\n\nAbstract:Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence. Reinforcement learning (RL) on the final answer cannot correct this, because a guess earns the same reward as reading. We propose Cross-Input Relative Policy Optimization (CrossRPO), which trains agents on contrast sets. A contrast set asks one question about several versions of an image that differ only in a small region with the evidence and have different answers, so only reading the evidence solves the whole set. CrossRPO rewards solving the whole set, and we prove that it does not reinforce a set answered from common sense. We build contrast sets for training (ViRA-Train) and evaluation (ViRA-Bench) by editing one small object in images of 21 to 120 megapixels, and we photograph further sets with real changes (ViRA-Bench-Real) to exclude editing traces. We train two Visual Reasoning Agents, ViRA-9B and ViRA-27B, with CrossRPO on only about 3,500 items of ViRA-Train each. CrossRPO achieves 63.3% set accuracy on ViRA-Bench at the maximum resolution, against 59.3% for GRPO. ViRA-9B is the most accurate open model of its size on all benchmarks, and ViRA-27B outperforms Claude Haiku 5.5 and GPT-6-Luna, both at their highest thinking level, on most benchmarks.\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/vira-toward-ultra-high-resolution-visual-agents-via-cross-input-relative-policy", "canonical_source": "http://arxiv.org/abs/2611.21605v1", "published_at": "2026-11-17 14:20:32+00:00", "updated_at": "2026-11-17 20:00:35.016441+00:00", "lang": "en", "topics": ["computer-vision", "ai-research", "machine-learning", "ai-agents", "large-language-models"], "entities": ["ViRA", "CrossRPO", "ViRA-Bench", "ViRA-Train", "ViRA-9B", "ViRA-27B", "Claude Haiku 5.5", "GPT-6-Luna"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/vira-toward-ultra-high-resolution-visual-agents-via-cross-input-relative-policy", "markdown": "https://wpnews.pro/news/vira-toward-ultra-high-resolution-visual-agents-via-cross-input-relative-policy.md", "text": "https://wpnews.pro/news/vira-toward-ultra-high-resolution-visual-agents-via-cross-input-relative-policy.txt", "jsonld": "https://wpnews.pro/news/vira-toward-ultra-high-resolution-visual-agents-via-cross-input-relative-policy.jsonld"}}