Improving Multimodal Reasoning via Worst Dimension Optimization

Computer Science > Artificial Intelligence [Submitted on 5 Jun 2026] Improving Multimodal Reasoning via Worst Dimension Optimization Haocheng Lv, Huaping Zhang, Qiuchi Li, Lei Li, Chunxiao Gao Multimodal reasoning requires a path that retains integrity over a wide range of constraints, from visual grounding to logic consistency. However, the current Process Reward Models focus on heuristically defined rewards that equally weigh these factors, which may lead to the concealment of individual dimension failures by the dominating factors, without guaranteeing the validity of the reasoning process in general. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.07801 [cs.AI]   (or arXiv:2606.07801v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.07801 Focus to learn more Submission history From: Haocheng Lv [view email] [v1] Fri, 5 Jun 2026 19:32:23 UTC (1,088 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation 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 Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)