MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems

[2608.15006] MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2608.15006 (cs) [Submitted on 15 Aug 2026] Title: MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems Authors: Penghao Yin , Haomin Wang , Qihong Tang , Xiaoye Qu , Hongjie Zhang , Xiao-Ping Zhang View a PDF of the paper titled MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems, by Penghao Yin and 5 other authors View PDF HTML (experimental) Abstract: Although visual reasoning is crucial for solving complex geometry tasks, existing vision-language models rely heavily on text-only reasoning. Some recent methods introduce intermediate visual states to facilitate reasoning, but they are often hindered by inaccurate geometric representations and low rendering fidelity, ultimately leading to unreliable outputs. To address these limitations, we propose MetaReason, a framework for multimodal reasoning in plane geometry that leverages structured meta-information to enable accurate auxiliary-line construction. The framework first parses geometric images into meta-information, performs controllable edits with predefined tools to synthesize high-fidelity visual states, and then conducts reasoning based on these augmented views. To support this framework, we construct TutorGeo, a comprehensive dataset containing 17k image-to-meta conversion samples, 60k text-only reasoning traces, and 60k interleaved multimodal reasoning traces. Using this dataset, we combine supervised fine-tuning and reinforcement learning to develop robust multimodal reasoning capabilities. We also introduce ExamGeo, a benchmark derived from real-world examination problems that enables systematic evaluation across varying difficulty levels. Experimental results demonstrate that MetaReason significantly outperforms existing open-source models and achieves competitive performance against proprietary models. Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Multimedia (cs.MM) Cite as: arXiv:2608.15006 [cs.CV] (or arXiv:2608.15006v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.15006 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Penghao Yin [ view email ] [v1] Sat, 15 Aug 2026 03:24:13 UTC (6,514 KB) Full-text links: Access Paper: View a PDF of the paper titled MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems, by Penghao Yin and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.MM References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both 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. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems#612440
• TuringEnterprises/Open-MM-RL#786758
• MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse#342724
• Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs#31317
• From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning#997225