Preprint · 2025 · Open access
Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark
arXiv (Cornell University) · Published 4 December 2025 · DOI 10.48550/arxiv.2512.05091
In brief
“Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark” is a 2025 preprint by Haobo Yuan and 9 co-authors, published in arXiv (Cornell University). OpenAlex counts 14 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 14
- Most cited in
- 2026 (13)
- References
- 52
- Authors
- 10
Abstract
Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque; they typically output only final predictions without revealing the intermediate steps or fine-grained evidence (e.g., pixels, locations) that lead to the result. This contrasts with human intelligence, which naturally operates through a chain of visual reasoning. To address this limitation, we introduce the Visual Reasoning Tracer (VRT) task, which requires models to not only localize the target object but also explicitly predict the intermediate objects that form the reasoning path. To advance research in this area, we contribute: (1) VRT-Bench, a human-annotated benchmark for evaluating visual reasoning; (2) a new metric for assessing the quality of reasoning traces; and (3) VRT-80k, a large-scale dataset for reasoning model training. Our experiments reveal that while existing models often produce the correct final output, they struggle to ground their intermediate reasoning. In contrast, models trained on VRT-80k achieve substantial improvements in tracing the reasoning path.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Yuan, H., Yueyi, S., Li, Y., Zhang, T., Deng, X., Ding, H., Lu, Q., Wang, A., Li, X., & Yang, M.-H. (2025). Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.05091
MLA 9
Yuan, Haobo, et al. “Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2512.05091.
Chicago
Yuan, Haobo, Sun, Yueyi, Yanwei Li, Tao Zhang, Xueqing Deng, Henghui Ding, Qi Lu, Anran Wang, Xiangtai Li, and Ming-Hsuan Yang. 2025. “Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.05091.
Harvard
Yuan, H. et al. (2025) ‘Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark’, arXiv (Cornell University). doi:10.48550/arxiv.2512.05091.
IEEE
H. Yuan et al., “Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2512.05091.
BibTeX
@misc{yuan2025visual,
title = {{Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark}},
author = {Yuan, Haobo and Yueyi, Sun, and Li, Yanwei and Zhang, Tao and Deng, Xueqing and Ding, Henghui and Lu, Qi and Wang, Anran and Li, Xiangtai and Yang, Ming-Hsuan},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2512.05091},
url = {https://doi.org/10.48550/arxiv.2512.05091}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- visual reasoning
- multimodal large language models
- visual grounding
- visual question answering
- benchmark
- reasoning datasets
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Yuan, H., Yueyi, S., Li, Y., Zhang, T., Deng, X., Ding, H., Lu, Q., Wang, A., Li, X., & Yang, M.-H. (2025). Visual Reasoning Tracer: Object-Level Grounded Reasoning Benchmark. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.05091
How many times has this paper been cited?
14 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Haobo Yuan, Sun, Yueyi, Yanwei Li, Tao Zhang, Xueqing Deng, Henghui Ding, Qi Lu, Anran Wang, Xiangtai Li, Ming-Hsuan Yang.
What is the DOI of this paper?
10.48550/arxiv.2512.05091, permanently at https://doi.org/10.48550/arxiv.2512.05091. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.