SOURCE-LINKED INTELLIGENCE

Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed to enhance safety alignment, the stability of alignment mechanisms under extended reasoning remains underexplored. This paper challenges the prevailing view by revealing a critical vulnerability: Deep Reasoning May Induce Alignment Collapse. To rigorously quantify this phenomenon, we propose the Alignment Loss Rate (ALR) metric. Our experiments demonstrate that as reasoning depth increases, ALR rises significantly, indicating a severe degradatio

Read original source ↗ Open in workspace

recordType

paper

region

Global