Preprint · 2025 · Open access

VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors

Lyu, Wenbo, Yingjun Du, Zhao, Jinglin, Zhen, Xianton, Shao, Ling

arXiv (Cornell University) · Published 7 December 2025 · DOI 10.48550/arxiv.2512.06759

Open PDFView at the publisherCite this paper

In brief

“VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors” is a 2025 preprint by Lyu, Wenbo and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
3
Most cited in
2026 (3)
References
41
Authors
5

Abstract

Understanding multi-image, multi-turn scenarios is a critical yet underexplored capability for Large Vision-Language Models (LVLMs). Existing benchmarks predominantly focus on static or horizontal comparisons -- e.g., spotting visual differences or assessing appropriateness -- while relying heavily on language cues. Such settings overlook progressive, context-dependent reasoning and the challenge of visual-to-visual inference. To bridge this gap, we present VisChainBench, a large-scale benchmark designed to rigorously evaluate LVLMs' ability to perform multi-step visual reasoning across sequential, interdependent tasks with minimal language guidance. VisChainBench contains 1,457 tasks spanning over 20,000 images across three diverse domains (e.g., daily scenarios, engineering troubleshooting), structured to mimic real-world decision-making processes. Uniquely, the benchmark is constructed using a multi-agent generation pipeline, ensuring high visual diversity and controlled language bias. All the benchmark data and code for benchmark construction are available for viewing and download via following Link: https://huggingface.co/datasets/eyehole/VisChainBench

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wenbo, L., Du, Y., Jinglin, Z., Xianton, Z., & Ling, S. (2025). VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.06759

MLA 9

Wenbo, Lyu,, et al. “VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2512.06759.

Chicago

Wenbo, Lyu,, Yingjun Du, Zhao, Jinglin, Zhen, Xianton, and Shao, Ling. 2025. “VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.06759.

Harvard

Wenbo, L. et al. (2025) ‘VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors’, arXiv (Cornell University). doi:10.48550/arxiv.2512.06759.

IEEE

L. Wenbo, Y. Du, Z. Jinglin, Z. Xianton, and S. Ling, “VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2512.06759.

BibTeX

@misc{wenbo2025vischainbench,
  title     = {{VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors}},
  author    = {Wenbo, Lyu, and Du, Yingjun and Jinglin, Zhao, and Xianton, Zhen, and Ling, Shao,},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2512.06759},
  url       = {https://doi.org/10.48550/arxiv.2512.06759}
}

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

  • multi-turn reasoning
  • large vision-language models
  • benchmark design
  • language bias

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Wenbo, L., Du, Y., Jinglin, Z., Xianton, Z., & Ling, S. (2025). VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.06759

How many times has this paper been cited?

3 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?

Lyu, Wenbo, Yingjun Du, Zhao, Jinglin, Zhen, Xianton, Shao, Ling.

What is the DOI of this paper?

10.48550/arxiv.2512.06759, permanently at https://doi.org/10.48550/arxiv.2512.06759. 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.