arXiv cs.MA· Hyejun Jeong, Amir Houmansadr, Shlomo Zilberstein, Eugene Bagdasarian·· 10 天前AI 评分27
说服传播：说服会改变 AI 智能体的行为吗？
Persuasion Propagation: Does Persuasion Change AI Agent Behavior?
AI 导读
研究提出"说服传播"现象：与任务无关的说服性对话会在 AI 智能体后续任务执行中留下可测量的行为痕迹。在网页研究任务中，执行时间比基线增加 56%、访问域名增加 16.3%；编码任务则执行更快但修改量更大。对说服性对话更敏感的智能体并不能可靠预测下游行为变化的幅度，作者因此主张对 AI 智能体开展行为层面的说服评估。
正文 · 原文
Abstract:AI agents combine normal conversation with autonomous task execution, allowing earlier context to shape how later tasks are executed. Yet studying this possibility is challenging because agent behavior is noisy and costly to reproduce, and observed behavioral changes can be difficult to separate from generic context sensitivity. We first ask whether task-irrelevant persuasion changes how agents act, a phenomenon we call \emph{persuasion propagation}, and whether persuasion susceptibility explains variation in these effects. We show that persuasive interaction leaves a measurable, task-dependent behavioral footprint on downstream agent execution. In web research, it increases execution time by 56\% and domains visited by 16.3\% relative to a baseline, while coding shows faster execution with larger revisions. However, agents that are more susceptible to persuasive conversational context do not reliably predict the magnitude of the downstream behavioral shifts. This motivates behavior-level evaluation of persuasion in AI agents.
| Comments: | Code available at this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2602.00851 [cs.AI] |
| (or arXiv:2602.00851v4 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2602.00851 arXiv-issued DOI via DataCite |
Submission history
From: Hyejun Jeong [view email]
[v1]
Sat, 31 Jan 2026 18:33:14 UTC (4,291 KB)
[v2]
Sun, 15 Feb 2026 22:45:36 UTC (4,291 KB)
[v3]
Thu, 21 May 2026 00:39:39 UTC (4,288 KB)
[v4]
Wed, 7 Oct 2026 00:39:47 UTC (423 KB)
来源：arXiv cs.MA · arxiv.org