Preprint · 2025 · Open access
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
arXiv (Cornell University) · Published 10 January 2025 · DOI 10.48550/arxiv.2501.06186
In brief
“LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs” is a 2025 preprint by Omkar Thawakar and 14 co-authors, published in arXiv (Cornell University). OpenAlex counts 146 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 146
- Most cited in
- 2025 (95)
- References
- 51
- Authors
- 15
Abstract
Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual reasoning and do not emphasize step-wise problem-solving. To this end, we propose a comprehensive framework for advancing step-by-step visual reasoning in large language models (LMMs) through three key contributions. First, we introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks. The benchmark presents a diverse set of challenges with eight different categories ranging from complex visual perception to scientific reasoning with over 4k reasoning steps in total, enabling robust evaluation of LLMs' abilities to perform accurate and interpretable visual reasoning across multiple steps. Second, we propose a novel metric that assesses visual reasoning quality at the granularity of individual steps, emphasizing both correctness and logical coherence. The proposed metric offers deeper insights into reasoning performance compared to traditional end-task accuracy metrics. Third, we present a new multimodal visual reasoning model, named LlamaV-o1, trained using a multi-step curriculum learning approach, where tasks are progressively organized to facilitate incremental skill acquisition and problem-solving. The proposed LlamaV-o1 is designed for multi-step reasoning and learns step-by-step through a structured training paradigm. Extensive experiments show that our LlamaV-o1 outperforms existing open-source models and performs favorably against close-source proprietary models. Compared to the recent Llava-CoT, our LlamaV-o1 achieves an average score of 67.3 with an absolute gain of 3.8\% across six benchmarks while being 5 times faster during inference scaling. Our benchmark, model, and code are publicly available.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Thawakar, O., Dissanayake, D., More, K., Thawkar, R., Heakl, A., Ahsan, N., Yuhao, L., Zumri, M., Lahoud, J., Anwer, R. M., Cholakkal, H., Laptev, I., Shah, M., Khan, F. S., & Khan, S. (2025). LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.06186
MLA 9
Thawakar, Omkar, et al. “LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2501.06186.
Chicago
Thawakar, Omkar, Dinura Dissanayake, Ketan More, Ritesh Thawkar, Ahmed Heakl, Noor Ahsan, Li, Yuhao, et al. 2025. “LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.06186.
Harvard
Thawakar, O. et al. (2025) ‘LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs’, arXiv (Cornell University). doi:10.48550/arxiv.2501.06186.
IEEE
O. Thawakar et al., “LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2501.06186.
BibTeX
@misc{thawakar2025llamav,
title = {{LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs}},
author = {Thawakar, Omkar and Dissanayake, Dinura and More, Ketan and Thawkar, Ritesh and Heakl, Ahmed and Ahsan, Noor and Yuhao, Li, and Zumri, Mohammed and Lahoud, Jean and Anwer, Rao Muhammad and Cholakkal, Hisham and Laptev, Ivan and Shah, Mubarak and Khan, Fahad Shahbaz and Khan, Salman},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2501.06186},
url = {https://doi.org/10.48550/arxiv.2501.06186}
}
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
- large language models
- curriculum learning
- scientific reasoning
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?
Thawakar, O., Dissanayake, D., More, K., Thawkar, R., Heakl, A., Ahsan, N., Yuhao, L., Zumri, M., Lahoud, J., Anwer, R. M., Cholakkal, H., Laptev, I., Shah, M., Khan, F. S., & Khan, S. (2025). LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.06186
How many times has this paper been cited?
146 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?
Omkar Thawakar, Dinura Dissanayake, Ketan More, Ritesh Thawkar, Ahmed Heakl, Noor Ahsan, Li, Yuhao, Mohammed Zumri, Jean Lahoud, Rao Muhammad Anwer, Hisham Cholakkal, Ivan Laptev and 3 more.
What is the DOI of this paper?
10.48550/arxiv.2501.06186, permanently at https://doi.org/10.48550/arxiv.2501.06186. 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.