The paper investigates how visual presentation affects vision‑language models (VLMs) on the SPaRC spatial planning benchmark. By adding lightweight input‑side scaffolds that keep the visual modality but make spatial structure clearer, the authors achieve up to a 34.0‑percentage‑point accuracy boost across multiple VLMs, and an additional 4.6 points when combined with GRPO training. Analyses reveal that these improvements stem mainly from reduced grounding errors, while rule‑based reasoning remains difficult, highlighting visual presentation as a key determinant of whether VLM benchmarks test grounded perception, downstream reasoning, or both.
By Lars Benedikt Kaesberg, Tianyu Yang, Florian Valentin Wunderlich, Terry Ruas, Jan Philip Wahle, Daniel Kurzawe, Bela Gipp
arXiv:2510.09302v2 Announce Type: replace-cross
Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable success in difficult purely textual mathematical reasoning tasks, eve...
By Yuying Li, Siyi Qian, Hao Liang, Leqi Zheng, Ruichuan An, Linzhuang Sun, Jiajun Zhang, Wentao Zhang
arXiv:2604. 04917v3 Announce Type: replace-cross Abstract: What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks?
By Gabriel Sarch, Linrong Cai, Qunzhong Wang, Haoyang Wu, Danqi Chen, Zhuang Liu
arXiv:2606. 03626v1 Announce Type: cross Abstract: Vision-language models (VLMs) have been explored for visual programming, where they generate code to solve visual tasks.
By Chao Wen, Jacqueline Staub, Adish Singla
The paper introduces a new benchmark for diagrammatic reasoning in olympiad geometry, comprising 954 self‑contained problems and a 297‑problem hard subset. Each problem is paired with a human‑authored, high‑fidelity diagram in Asymptote code and a suite of metrics for evaluating diagram construction. Experiments show that current foundation models excel at solving the problems but produce markedly less faithful diagrams, with an average compile success rate of only 36.14%.
By Hsien Xin Peng, Anthony Kim, Alvin Li, Calvin Supasanya, Shivank Garg, Kevin Zhu
arXiv:2607. 00491v1 Announce Type: cross Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input.
By Leyuan Yu, Xiao Tang, Minghao Liu, Xinyuan Li, Xiaokai Bai, Sheng Zhou, Qunshu Lin, Weihao Xuan, Naoto Yokoya
arXiv:2609.14473v1 Announce Type: new
Abstract: Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical...
By Avijit Dasgupta, Shayon Dasgupta, Zakaria Laskar, C. V. Jawahar, Karteek Alahari
Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions, where action semantics depend on coordinated roles and spatial-te...
arXiv:2610.01605v1 Announce Type: cross
Abstract: Reliable visual reasoning requires composing multiple visual observations and returning consistent answers to logically equivalent questions. We intr...
By Yuzhou Wang, Emile Anand, Ijay Narang
arXiv:2606. 07861v1 Announce Type: cross Abstract: Recent vision-language models (VLMs) excel at multimodal understanding and reasoning, yet their fine-grained visual perception remains underexplored.
By Lujun Li, Lama Sleem, Niccolo Gentile, Yangjie Xu, Yewei Song, Wenbo Wu, Radu State
arXiv:2608. 14741v1 Announce Type: cross Abstract: We introduce PolyComp, a procedurally generated and verified benchmark that stresses visual recognition and compositional spatial reasoning.
By Siddharth Patel
The paper introduces DoublesEval, a diagnostic framework that uses professional doubles badminton to test visual‑language models’ ability to reason about dynamic multi‑agent interactions. It decomposes rallies into key moments and evaluates models across four dimensions—atomic recognition, intra‑segment composite understanding, cross‑segment causal reasoning, and high‑level tactical abstraction—highlighting specific reasoning failures. The authors also propose TacticCheck, a lightweight consistency checker that improves performance without retraining the models, yet significant gaps remain in tactical reasoning.
By Jintao Cheng, Weibin Li