English(EN) Prompt Sensitivity of Generative Agents: Evidence from an Epidemic Model

生成式AI代理在流行病模拟中表现出对提示词变化的敏感性

作者 PulseAugur 编辑部 · [2 个来源] · 2026-08-26 12:42

一项发表在arXiv上的新研究调查了生成式AI代理在模拟人类行为（特别是在流行病模型的背景下）时对提示词变化的敏感程度。研究发现，虽然同义提示词对模拟流行病的结果影响甚微，但微小的提示词变化和上下文转移确实会影响结果。研究还表明，分配给这些代理的身份名称并未显著改变流行病的进程。 AI

影响这项研究强调了在研究环境中，精确的提示词对于可靠的AI代理模拟的重要性。

排序理由该集群包含一篇发表在arXiv上的研究论文，详细介绍了关于生成式AI代理的发现。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 该集群包含一篇发表在arXiv上的研究论文，详细介绍了关于生成式AI代理的发现。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 12 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Ross Williams, Niyousha Hosseinichimeh · 2026-08-28 04:00

生成式智能体的提示词敏感性：来自流行病模型的证据

arXiv:2608.26221v1 Announce Type: cross Abstract: As generative AI gains traction, researchers are investigating its potential to serve as proxies for humans. From undergoing cognitive psychology experiments to experiencing an epidemic, generative agents, agents powered by genera…
arXiv cs.MA (Multiagent) TIER_1 English(EN) · Niyousha Hosseinichimeh · 2026-08-26 12:42

生成式智能体的提示词敏感性：来自流行病模型的证据

As generative AI gains traction, researchers are investigating its potential to serve as proxies for humans. From undergoing cognitive psychology experiments to experiencing an epidemic, generative agents, agents powered by generative AI models, produce realistic human behavior w…