The paper introduces Auto-Comp, a fully automated, concept-driven pipeline that generates photorealistic compositional benchmarks for vision‑language models. Auto‑Comp creates paired Minimal and Contextual samples for each concept, enabling isolation of core binding abilities from visio‑linguistic complexity. Evaluations across 25 models reveal consistent failures in attribute and relational binding, with context helping relational tasks but hindering attribute tasks due to visual clutter.
By Cristian Sbrolli, Toshihiko Yamasaki, Matteo Matteucci
PhysElite is a new bilingual multimodal benchmark designed to evaluate large language models on Olympiad-level physics problems. It contains 11,586 problems, each paired with visual diagrams, step-by-step bilingual Chinese‑English solution derivations, and the final answer. Benchmarking 18 models revealed that even the best reaches only 33.7% accuracy, and a step‑level analysis highlights where models falter in reasoning.
By Ruoran Xu, Wending Gao, Liyunfeng Chen, Aixin Shi, Haoyu Cheng, Zixiang Fang, Yiqiang Zou, Qiufeng Wang
arXiv:2607. 15176v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet current evaluations remain largely chart-centric and provide limited evidence of understanding of scientific visualization (SciVis).
By Patrick Phuoc Do, Chau M. Ta, Chaoli Wang
arXiv:2609.13158v1 Announce Type: new
Abstract: Large Vision--Language Models (LVLMs) are increasingly expected to perform visual question answering (VQA) over planar media. However, existing planar...
By Yongqi Yu, Yu Zhang
arXiv:2609.14779v1 Announce Type: new
Abstract: Performing deliberate mathematical reasoning in visual contexts is a hallmark of advanced Multimodal Large Language Models (MLLMs) and requires a sophi...
By Mingze Yin, Xiaohan Wang, Dian Li, Haichao Yao, Yilin Zhao, Youjun Chen, Gang Liu, Jintai Chen, Yiheng Zhu, Chang-Yu Hsieh, Aimin Pan
arXiv:2508.13680v5 Announce Type: replace-cross
Abstract: We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (V...
By Vy Tuong Dang, An Vo, Emilio Villa-Cueva, Quang Tau, Duc Dm, Thamar Solorio, Daeyoung Kim
arXiv:2606. 04244v1 Announce Type: new Abstract: Multimodal large language models are increasingly capable of complex reasoning, yet their performance often degrades when they must externalize a problem through a tool and then reason over the tool's output, specifically when they rely on visual aids.
By Amirhossein Dabiriaghdam, Shayan Vassef, Mohammadreza Bakhtiari, Yasamin Medghalchi, Ilker Hacihaliloglu, Mesrob Ohannessian, Lele Wang, Giuseppe Carenini
CoVA‑SFT is a new large‑scale dataset comprising 51.9K samples and over 222K multimodal reasoning steps that teach models to interleave text and visual abstractions across five layout families and 17 complex tasks. It includes explicit rationale formulations, agentic renderings, and verification loops to help models build and maintain internal visual workspaces for purely textual reasoning problems. A companion benchmark, CoVA‑Bench, contains 1,700 held‑out test samples for reproducible evaluation, and models fine‑tuned on CoVA‑SFT outperform all interleaved CoT baselines by more than 2× on average, though they still lag behind strong text‑only CoT baselines.
By Tsung-Han Wu, Heekyung Lee, Anya Ji, Haoming Chen, Trevor Darrell, Joseph E. Gonzalez, David M. Chan
arXiv:2603. 29139v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have enabled agentic systems to translate natural-language intent into executable scientific visualization (SciVis) tasks.
By Kuangshi Ai, Haichao Miao, Kaiyuan Tang, Nathaniel Gorski, Jianxin Sun, Guoxi Liu, Helgi I. Ingolfsson, David Lenz, Hanqi Guo, Hongfeng Yu, Teja Leburu, Michael Molash, Bei Wang, Tom Peterka, Chaoli Wang, Shusen Liu
arXiv:2512. 11995v2 Announce Type: replace-cross Abstract: While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in most benchmarks, they often struggle in practice with complex open-ended tasks, which usually require multiple rounds of exploration and reasoning in the visual space.
By Chenrui Fan, Yijun Liang, Shweta Bhardwaj, Kwesi Cobbina, Ming Li, Tianyi Zhou
arXiv:2506. 03922v4 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains.
By Zhaolu Kang, Junhao Gong, Jiaxu Yan, Wanke Xia, Yian Wang, Ziwen Wang, Huaxuan Ding, Zhuo Cheng, Wenhao Cao, Zhiyuan Feng, Siqi He, Shannan Yan, Junzhe Chen, Xiaomin He, Chaoya Jiang, Wei Ye, Kaidong Yu, Xuelong Li
arXiv:2608. 08964v1 Announce Type: new Abstract: The generation of mathematically precise diagrams from tex- tual prompts has emerged as a critical yet underexplored capability of Large Language Models (LLMs).
By Harish Kashyap, Kiran Byadarhaly, Sriram Chakaravarthy, Sanyukta Tuti, Aryan Mistry