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
Multimodale große Sprachmodelle (MLLMs) haben rasche Fortschritte bei der visuellen Argumentation gemacht, aber viele Aufgaben erfordern Beweise, die nur durch interne Argumentation schwer zu erhalten sind: Unsere kontrollierte Studie zu 22 Benchmarks zeigt, dass die einfache Erhöhung des Inferenzbudgets des Basismodells nur bescheidene Gewinne bringt.
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