SOURCE-LINKED INTELLIGENCE

Assessing Adversarial Robustness of Latent Reasoning Models

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Large language models increasingly rely on long chain-of-thought (CoT) trajectories for complex reasoning, but autoregressive generation brings substantial memory and inference costs. Latent reasoning models (LRMs) offer a more efficient alternative by compressing intermediate reasoning into a small number of continuous latent vectors. Despite their efficiency, however, the adversarial robustness of LRMs remains largely underexplored. In this work, we systematically evaluate the robustness of latent reasoning across textual and multimodal settings, covering eight models and six benchmarks. We

Read original source ↗ Open in workspace

recordType

paper

region

Global