Yu Zhou, Cheng-Fu Yang, Rui Sun, Di Wu, Sibo Peng, Mingyang Zhang, Zhen Yang, Ruiyi Zhang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26860 · open-access PDF
وقد نجحت النماذج الكبيرة المتعددة اللغات المتعددة اللغات (MLLMs) بسرعة في التفكير المرئي، لكن العديد من المهام تحتاج إلى الأدلة التي من الصعب الحصول عليها من خلال التفكير الداخلي وحدها: أظهرت دراستنا المعتمدة على 22 مقارنة أن زيادة ميزانية التفكير بسهولة في نمو النماذج الأساسية تؤدي فقط إلى مزيد من الأرباح.
Machine translation (Meta M2M100); the English original follows.
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmarks shows that simply increasing the inference budget of the base model yields only modest gains. Such tasks demand grounded perception, external knowledge, and numerical measurements obtained through heterogeneous tools, whose outputs must be made interpretable to the model and retained across reasoning steps. We introduce OpenVLHarness, a multimodal reasoning harness organized aro
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26860, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange