研究人员为多智能体LLM系统开发了一个新的统计框架，该系统用于自残风险评估等关键应用。该框架结构为有向无环图（DAG），提供自适应决策能力，以提高相对于传统方法的可靠性。它包含了对单个智能体更严格的置信度界限以及一种基于老虎机（bandit-based）的采样策略，该策略会根据输入的难度进行调整，从而显著减少了误报。 AI
影响 通过在不牺牲召回率的情况下减少误报，提高了安全关键型LLM应用的精确度。
排序理由 学术论文，详细介绍了多智能体LLM系统的新统计框架。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.22154v1 Announce Type: new Abstract: Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do…
Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not indicate when a decision is reliable or how…