Keywords
confidence gating
visual-text disagreement
paired simulation
reproducibility
Abstract
We evaluated confidence gating for multimodal decision support under 11% visual-text disagreement. A deterministic paired simulation generated 72 cases and preserved a low-signal stratum. Mean decision consistency changed from 0.584 to 0.625; the paired difference was +0.041 (95% interval +0.039 to +0.044). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Dai, Y., Peng, X., Wang, Y., Nakov, P., & Xie, Z. (2026). Seeing Is Not Deciding: Can Multimodal LLMs Act as Effective CEOs? arXiv preprint arXiv:2608.05864. arXiv. https://doi.org/10.48550/arXiv.2608.05864
Srisuk, P. (2026). WiDM-LLM: Wireless Decision-Making with Large Language Models for 6G Communication Systems. https://doi.org/10.2139/ssrn.7181158
Guo, X., Chen, P., Liang, S., Jiao, Z., Li, L., Yan, J., Huang, Y., Liu, Y., & Fan, W. (2022). PaCAR: COVID-19 Pandemic Control Decision Making via Large-Scale Agent-Based Modeling and Deep Reinforcement Learning. Medical Decision Making, 42(8), 1064-1077. https://doi.org/10.1177/0272989x221107902
Manish Rana (2026). Adaptive Decision Intelligence through Retrieval-Augmented Multi-Agent Large Language Models. Journal of Intelligent Decision Making and Information Science, 3(8s), 1955-1977. https://doi.org/10.59543/jidmis.v3.2250
Jiang, T., Wu, J., & Leung, S. C. H. (2025). The cognitive impacts of large language model interactions on problem solving and decision making using EEG analysis. Frontiers in Computational Neuroscience, 19, 1556483. https://doi.org/10.3389/fncom.2025.1556483
Liao, T., Fang, X., Feng, Y., & Wang, S. (2026). Reliable and Efficient Decision-Making for Large Language Model Agents through Uncertainty-Guided Adaptive Reasoning. https://doi.org/10.2139/ssrn.6844659
Kuerbanjiang, W., Wang, X., Jiamaliding, Y., Maimaitiaili, M., & Yi, Y. (2025). Multidisciplinary large language model agent teams for precision oncology enhance complex gynecologic oncology decision support. https://doi.org/10.1101/2025.10.30.25339199
Nargesi, A., Kitonyo, J., Maddah, M., & Ellinor, P. (2025). A large language model agent for multimodal evaluation of cardiovascular disease. European Heart Journal, 46(Supplement_1), ehaf784.4504. https://doi.org/10.1093/eurheartj/ehaf784.4504
Goel, P. K. (2025). Security and Privacy Challenges in Multi-Agent Language Model Ecosystems. Advances in Computational Intelligence and Robotics, 209-224. https://doi.org/10.4018/979-8-3373-1419-8.ch008
Sissodia, R., Dwivedi, V., & Verma, T. (2025). Advancements in Multi-Agent Large Language Model Systems for Next-Generation AI. Advances in Computational Intelligence and Robotics, 1-32. https://doi.org/10.4018/979-8-3373-1419-8.ch001