Journal article · 2026 · Open access
Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools
IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–17 · Published 21 October 2026 · DOI 10.1109/tpami.2026.3745877
In brief
“Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools” is a 2026 journal article by Xiuwei Chen and 10 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 1 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 1
- Most cited in
- 2026 (1)
- Field-weighted impact
- 1.14
- References
- 67
- Authors
- 11
Abstract
Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the "Thinking with Images" (TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, which leads to substantial computational overhead and inference latency. Furthermore, existing models generally lack capability boundary awareness, making it difficult to adaptively determine when to rely on internal parametric knowledge and when to invoke external tools. To address these issues, we propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability. BEE directly incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism. This design enables the model to adaptively balance internal knowledge and implicit tools, avoiding redundant tool usage while substantially reducing inference latency. Specifically, BEE involves a two-stage training process: (1) Formalized Chain-of-Thought (CoT) Supervised Fine-tuning (SFT). We construct CoT trajectories with structured tool slots and mixed invocation states. This stage activates the model's implicit tool representations and adaptive switching capability. (2) Self-regulated Reward-Driven Alignment. To address redundant tool usage caused by ambiguous cognitive boundaries, we first introduce the Net Tool Gain (NTG) metric to quantify this phenomenon. Based on this observation, we further propose a self-regulated reward mechanism. This mechanism penalizes ineffective tool dependency and encourages the model to perform knowledge routing, ensuring that implicit tools are invoked only when the model's internal knowledge is insufficient. BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks and achieving substantial gains in inference efficiency. In particular, under the high-resolution setting of 8192, BEE achieves up to $\sim 86.2\%$ inference acceleration compared with the DeepEyes method. BEE provides a promising direction for developing implicit tool MLLMs that combine strong cognitive ability with extremely low latency and further advances the development of self-regulated MLLMs.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chen, X., Chen, Q., Hu, W., Chen, Z., Xiang, K., Ma, Z., Zhang, M., Han, J., Li, H., Xu, H., & Liang, X. (2026). Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–17. https://doi.org/10.1109/tpami.2026.3745877
MLA 9
Chen, Xiuwei, et al. “Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–17. https://doi.org/10.1109/tpami.2026.3745877.
Chicago
Chen, Xiuwei, Quanlin Chen, Wentao Hu, Zisheng Chen, Kun Xiang, Zehua Ma, Mingyang Zhang, et al. 2026. “Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–17. https://doi.org/10.1109/tpami.2026.3745877.
Harvard
Chen, X. et al. (2026) ‘Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–17. doi:10.1109/tpami.2026.3745877.
IEEE
X. Chen et al., “Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–17, 2026, doi: 10.1109/tpami.2026.3745877.
BibTeX
@article{chen2026beyond,
title = {{Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools}},
author = {Chen, Xiuwei and Chen, Quanlin and Hu, Wentao and Chen, Zisheng and Xiang, Kun and Ma, Zehua and Zhang, Mingyang and Han, Jianhua and Li, Hanhui and Xu, Hang and Liang, Xiaodan},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {PP},
pages = {1--17},
doi = {10.1109/tpami.2026.3745877},
url = {https://doi.org/10.1109/tpami.2026.3745877}
}
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
- multimodal large language models
- inference latency reduction
- chain-of-thought fine-tuning
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?
Chen, X., Chen, Q., Hu, W., Chen, Z., Xiang, K., Ma, Z., Zhang, M., Han, J., Li, H., Xu, H., & Liang, X. (2026). Beyond the Eye: Efficient Multimodal Reasoning Via Self-Regulated Implicit Visual Tools. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–17. https://doi.org/10.1109/tpami.2026.3745877
How many times has this paper been cited?
1 times, according to OpenAlex on 18 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?
Xiuwei Chen, Quanlin Chen, Wentao Hu, Zisheng Chen, Kun Xiang, Zehua Ma, Mingyang Zhang, Jianhua Han, Hanhui Li, Hang Xu, Xiaodan Liang.
What is the DOI of this paper?
10.1109/tpami.2026.3745877, permanently at https://doi.org/10.1109/tpami.2026.3745877. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 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.