AI RESEARCH
Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models
arXiv CS.AI
•
ArXi:2604.13206v1 Announce Type: new As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical instability has emerged as a critical reliability issue. While recent studies have nstrated the significant downstream effects of these instabilities, the root causes and underlying mechanisms remain poorly understood.