The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem.However, the understanding of LLM decisionmaking 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).Our study, which involves 20 frontier and open LLMs, is complemented by a matched human subjects experiment, which provides one reference point, while an expected payoff maximizing rational agent model provides another.We find that LLMs cluster into two categories: reasoning models (RMs) and conversational models (CMs).RMs tend towards rational behavior, are insensitive to the order of prospects, gain/loss framing, and explanations, and behave similarly whether prospects are explicit or presented via a history of outcomes.CMs are significantly less rational, slightly more human-like, sensitive to prospect ordering, framing, and explanation, and exhibit a large description-history gap.Paired comparisons of open LLMs suggest that a key factor differentiating RMs and CMs is training for mathematical reasoning.

This paper focuses on home smart voice devices to address the problems of traditional mental health diagnosis and evaluation (e.g., the inability to monitor, analyze and assess mental health in real-time and the heavy reliance on psychologists and counselors for judgment). It constructs a model for monitoring, examining, and evaluating children's mental health using interactive communication and voice recordings between children and intelligent voice devices. The model uses techniques such as natural language processing and data mining based on a random forest algorithm. Meanwhile, this paper explores and investigates the feasibility of implementing the model on the ground in terms of technology development and technology preference.