AI RESEARCH

Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

arXiv CS.AI

ArXi:2602.15173v2 Announce Type: replace The use of large language models either as decision systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We study LLM risky choices along two dimensions: (1) prospect representation (based on an explicit representation or outcome history) and (2) decision rationale (explanation