CORTEXA
← Browse
arxivcs.CV2026-07-22

Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning

Md Tanvirul Alam

Reinforcement learning with verifiable rewards (RLVR) has substantially improved language-model reasoning, yet its extension to vision-language models remains constrained by the lack of training data that are simultaneously broad, exactly verifiable, and reproducible. We introduce Trace, a taxonomy-guided environment for multidomain visual reasoning. Trace factorizes task construction into a scene grammar and an executable task program, separating visual realization from answer computation. A shared semantic state determines the rendered image, prompt, typed answer, verifier state, and replayable instance trace. The resulting environment comprises 1,000 tasks over 277 scene grammars and 11 visual domains, with controlled semantic and visual variation. RLVR on 64,000 Trace instances improves the macro-average across 24 external benchmarks by 3.51 percentage points for Qwen2.5-VL-3B and 4.06 points for Qwen2.5-VL-7B, providing evidence that broad procedural training can transfer beyond the generated task distributions. Project page: https://maveryn.github.io/trace/.

View free PDFSource page

Related papers

arxivcs.CV2026-07-22

RS-RIE-Bench: Benchmarking Reasoning-Guided Remote Sensing Image Editing

Zihan Qin, Boao Xu, Zhao Dong, Yingping Sun, Ziheng Jiao, Junying Wang, et al.

Remote sensing image editing aims to modify remote sensing images according to natural language instructions while preserving geographic rules and sensor observation characteristics. Existing benchmarks mainly target natural images or general visual scenes, and thus may not fully…

View free PDFSource page
arxivcs.CV2026-07-23

Be Consistent! Enhancing Robust Visual Reasoning in LVLMs with Consistency Constraints

Liqiang Jing, Xiong Zhou, Siddharth Varia, Neha Anna John, Xinya Du, Vassilis N. Ioannidis

While Large Vision-Language Models (LVLMs) exhibit strong perceptual capabilities, they remain vulnerable in visual reasoning tasks. Existing benchmarks largely focus on symbolic mathematical or scientific problems and simple vision-centric tasks, offering limited assessment of c…

View free PDFSource page
arxivcs.CV2026-07-23

ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes?

Han Li, Si Liu, Zehao Huang, Dongxin Lyu, Longfei Xu, Jiahui Fu, et al.

Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse expert-level tasks, but they still struggle with fundamental abilities that humans naturally develop through continuous observation of the real world, such as spatial perception and dynamic r…

View free PDFSource page
arxivcs.CVcs.LG2026-07-31

SciFigPlag-Bench: A Benchmark for Provenance-Aware Scientific Figure Plagiarism Detection

Zhiying Cui, Minghao Yang, Linlin Gao, Jie Liu, Pengyuan Li

Scientific figures often encode the visual evidence behind scientific findings, yet figure plagiarism remains underexplored as a benchmarked multimodal evaluation problem. We present SciFigPlag-Bench, a benchmark for provenance-aware reasoning over scientific figures in scholarly…

View free PDFSource page
arxivcs.CV2026-07-21

Continual Video-MLLM Adaptation over Evolving Domains

Rui Cheng, Meixing Shi, Yuxiang Cai, Jingcai Guo, Jianwei Yin, Zhi Chen

Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the mode…

View free PDFSource page