Preprint · 2026 · Open access
See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs
arXiv (Cornell University) · Published 25 February 2026 · DOI 10.48550/arxiv.2602.21497
In brief
“See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs” is a 2026 preprint by Yongchang Zhang and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 0
- References
- 25
- Authors
- 5
Abstract
Recent large vision-language models (LVLMs) have demonstrated impressive reasoning ability by generating long chain-of-thought (CoT) responses. However, CoT reasoning in multimodal contexts is highly vulnerable to visual hallucination propagation: once an intermediate reasoning step becomes inconsistent with the visual evidence, subsequent steps-even if logically valid-can still lead to incorrect final answers. Existing solutions attempt to mitigate this issue by training models to "think with images" via reinforcement learning (RL). While effective, these methods are costly, model-specific, and difficult to generalize across architectures. Differently, we present a lightweight method that bypasses RL training and provides an iterative, training-free, plug-and-play framework for visually-grounded multimodal reasoning. Our key idea is to supervise each reasoning step at test time with visual evidence, ensuring that every decoded token is justified by corresponding visual cues. Concretely, we construct a textual visual-evidence pool that guides the model's reasoning generation. When existing evidence is insufficient, a visual decider module dynamically extracts additional relevant evidence from the image based on the ongoing reasoning context, expanding the pool until the model achieves sufficient visual certainty to terminate reasoning and produce the final answer. Extensive experiments on multiple LVLM backbones and benchmarks demonstrate the effectiveness of our approach. Our method achieves 16.5%-29.5% improvements on TreeBench and 13.7% RH-AUC gains on RH-Bench, substantially reducing hallucination rates while improving reasoning accuracy without additional training.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhang, Y., Ma, O., Liu, T., Zhou, G., & Chen, Y. (2026). See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.21497
MLA 9
Zhang, Yongchang, et al. “See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2602.21497.
Chicago
Zhang, Yongchang, Oliver Ma, Tianyi Liu, GuangQuan Zhou, and Yang Chen. 2026. “See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.21497.
Harvard
Zhang, Y. et al. (2026) ‘See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs’, arXiv (Cornell University). doi:10.48550/arxiv.2602.21497.
IEEE
Y. Zhang, O. Ma, T. Liu, G. Zhou, and Y. Chen, “See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2602.21497.
BibTeX
@misc{zhang2026sorted,
title = {{See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs}},
author = {Zhang, Yongchang and Ma, Oliver and Liu, Tianyi and Zhou, GuangQuan and Chen, Yang},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2602.21497},
url = {https://doi.org/10.48550/arxiv.2602.21497}
}
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 vision-language models
- multimodal reasoning
- long chain-of-thought
- visual hallucinations
- training-free reasoning
- iterative 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?
Zhang, Y., Ma, O., Liu, T., Zhou, G., & Chen, Y. (2026). See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.21497
How many times has this paper been cited?
0 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?
Yongchang Zhang, Oliver Ma, Tianyi Liu, GuangQuan Zhou, Yang Chen.
What is the DOI of this paper?
10.48550/arxiv.2602.21497, permanently at https://doi.org/10.48550/arxiv.2602.21497. 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.