As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We study this problem by introducing MIR-SafetyBench, the first benchmark focused on multi-image reasoning safety, which consists of 2,676 instances across a taxonomy of 9 multi-image relations. Our extensive evaluations on 19 MLLMs reveal a troubling trend: models with more advanced multi-image reasoning can be more vulnerable on MIR-SafetyBench. Beyond attack success rates, we find that many responses labeled as safe are superficial, often driven by misunderstanding or evasive, non-committal replies. We further observe that unsafe generations exhibit lower attention entropy than safe ones on average. This internal signature suggests a possible risk that models may over-focus on task solving while neglecting safety constraints. Our code and data are available at https://github.com/thu-coai/MIR-SafetyBench.
@article{arxiv.2601.14127,
title = {The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning},
author = {Renmiao Chen and Yida Lu and Shiyao Cui and Xuan Ouyang and Victor Shea-Jay Huang and Shumin Zhang and Chengwei Pan and Han Qiu and Minlie Huang},
journal= {arXiv preprint arXiv:2601.14127},
year = {2026}
}