研究人员开发了HawkesLLM，一个旨在管理代理文本模拟系统中语义不确定性的新框架。该框架将时间影响建模与文本生成分开，将代理交互的级联表示为一个网络。多元Hawkes过程用于模拟代理如何随时间激活以及哪些先前输出应影响未来提示，然后语言模型根据此时间选择生成新事件。 AI
影响 通过管理不确定性，引入了一种改进序列文本生成中语义对齐的新方法。
排序理由 该集群包含一篇详细介绍代理文本模拟新框架的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.24756v1 Announce Type: new Abstract: Language-model agents increasingly emit uncertainty signals throughout a trajectory, but existing agentic UQ evaluations often conflate ranking usefulness with probabilistic truthfulness. AUROC, AUPRC, risk-coverage, Trajectory ECE,…
arXiv:2605.23043v1 Announce Type: cross Abstract: Agentic text-simulation systems write in sequence, with each item becoming possible context for later steps. That makes uncertainty path-dependent: an early ambiguity can affect later outputs. This paper studies this problem with …
Agentic text-simulation systems write in sequence, with each item becoming possible context for later steps. That makes uncertainty path-dependent: an early ambiguity can affect later outputs. This paper studies this problem with HawkesLLM, a framework that separates temporal inf…